Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

‼️ Dirty Frag: A Universal Linux Local Privilege Escalation via Page-Cache Write Primitives GitHub: Patches: CVE-2026-43284: A page-cache write flaw in the Linux kernel's xfrm-ESP (IPsec) subsystem that lets a local user corrupt read-only file pages via in-place decryption on shared skb fragments CVE-2026-43500: A sibling page-cache write flaw... show more

Dark Web Informer

212,359 subscribers

18,534 просмотров • 2 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

I make unlimited landing pages with Claude Cowork for $0 😱 here's the system that turns one URL into a landing page for every possible angle: step 1: scrape your brand DNA → Firecrawl scrapes your site. trust signals, colors, fonts, the works → I pointed it at virlo and it pulled every proof element & visual system in 90 seconds → nothing hallucinated. everything traced back to your actual site step 2: figure out WHY your product works → not the features but the reason someone should care. → maps which claims you can back up vs ones you can't step 3: lock your brand voice → pulls your exact phrases, tone, language patterns → ran it on a client last week. they thought they wrote the page. they didn't. step 4: write the copy → hard ban list kills AI slop on sight ("unlock", "seamless", "revolutionize" = dead) → then cuts 20% of whatever it wrote. if a line doesn't earn its spot, it's gone. step 5: generate on-brand visuals → Bloom creates images that ACTUALLY match your brand (s/o Ray for hooking up FREE bloom credits, ill send you a link) → no stock photo energy. no purple AI gradients. no "two businesspeople shaking hands." step 6: build the page → single-file HTML. responsive. ready to roll. → routes layout by type. product, SaaS, lead gen, regulated all look different → one product. six angles. six pages. each one ships. step 7: QA gate → scores every page on proof, trust, copy, visuals, anti-slop → shippable, draft, or blocked. nothing goes live without passing. input: your URL output: unlimited landing pages w/ copy & brand images Steal Ads automates ads. this builds landers for each. money ad → money page. agencies charge $5-10K per landing page. this builds unlimited pages for $0. I packaged the entire system as the Landing Page Factory. 7 Claude skills: - site-extract (brand DNA via Firecrawl) - page-strategy (mechanism mapping + real claims) - brand-profile (your voice + your branding) - page-copy (conversion copy w/ slop ban) - page-visuals (on-brand images w/ Bloom) - page-build (multiple variations & layouts) - page-qa (shippability gate so it doesn't suck) also works with OpenClaw🦞, hermes (Nous Research) or any agent framework. giving it away free. comment PAGES + like + follow (must follow so i can DM)

Matthew Berman

134,686 просмотров • 3 месяцев назад

I just built a plugin with Claude Fable 5 that turns Claude Code into a $5,000/mo SEO consultant 🤯 9 skills, one plugin: it connects straight to your Search Console + GA4 data, finds the wins, ships the fixes, and renders a live SEO dashboard that looks like a $200/mo SaaS product. All inside Claude Code. Perfect for DTC brands and agencies sitting on months of Search Console data nobody has time to read. Right now, you probably can't answer: Which keywords are sitting on page 2, one title tag away from page 1, Which pages are bleeding traffic to redirect chains and broken canonicals, Which blog posts rank for commercial terms but never link to a product page. This plugin answers all of it from your live data, then ships the fixes: → Finds your page-2 keywords and ships the fix: new title, headings, content, paste-ready → Clusters every query into a hub-and-spoke content map with the gaps flagged → Drafts posts from your actual search data, not guesses → Writes dev tickets for redirect chains and slow pages, ranked by traffic at risk → Builds the internal links between your blog and your money pages → Flags toxic backlinks and ranks outreach targets → Drops a Monday report with 3 priorities before the client even asks → Renders it all as a one-file HTML dashboard with a 0-100 SEO health score No dashboard staring. No CSV archaeology. No $5K/mo retainer for a PDF. What you get: → Page-2 keywords moved to page 1 → A content calendar that fills itself from data → Dev tickets that write themselves → A live SEO dashboard on command Built 100% in Claude Code with Claude Fable 5. I put the entire build into a step-by-step Playbook: all 8 workflow prompts (including the dashboard), how to turn them into a plugin, and the full Google setup (Including the 2 landmines Google doesn't tell you about). Want access for free? > Like this post > Comment "SEO" And I'll send it over (must be following so I can DM)

I just built a plugin with Claude Fable 5 that turns Claude Code into a $5,000/mo SEO consultant 🤯 9 skills, one plugin: it connects straight to your Search Console + GA4 data, finds the wins, ships the fixes, and renders a live SEO dashboard that looks like a $200/mo SaaS product. All inside Claude Code. Perfect for DTC brands and agencies sitting on months of Search Console data nobody has time to read. Right now, you probably can't answer: Which keywords are sitting on page 2, one title tag away from page 1, Which pages are bleeding traffic to redirect chains and broken canonicals, Which blog posts rank for commercial terms but never link to a product page. This plugin answers all of it from your live data, then ships the fixes: → Finds your page-2 keywords and ships the fix: new title, headings, content, paste-ready → Clusters every query into a hub-and-spoke content map with the gaps flagged → Drafts posts from your actual search data, not guesses → Writes dev tickets for redirect chains and slow pages, ranked by traffic at risk → Builds the internal links between your blog and your money pages → Flags toxic backlinks and ranks outreach targets → Drops a Monday report with 3 priorities before the client even asks → Renders it all as a one-file HTML dashboard with a 0-100 SEO health score No dashboard staring. No CSV archaeology. No $5K/mo retainer for a PDF. What you get: → Page-2 keywords moved to page 1 → A content calendar that fills itself from data → Dev tickets that write themselves → A live SEO dashboard on command Built 100% in Claude Code with Claude Fable 5. I put the entire build into a step-by-step Playbook: all 8 workflow prompts (including the dashboard), how to turn them into a plugin, and the full Google setup (Including the 2 landmines Google doesn't tell you about). Want access for free? > Like this post > Comment "SEO" And I'll send it over (must be following so I can DM)

Mike Futia

79,667 просмотров • 1 месяц назад

Harry Dry is the best copywriter I know. He's built a 130,000-person newsletter teaching people how to do it, and by the end of this interview, you'll be at least a Green Belt in copywriting. Some of his rules for writing: 1) A great sentence is a good sentence made shorter. 2) Writing great copy begins with having something to say in the first place. 3) Copy is like food. How it looks matters. 4) Since the look of copy matters so much, don't write copy in Google Docs. Write it in Figma (so you can write and design at the same time). 5) Kaplan's Law of Words: Any word that isn't working for you is working against you. 6) You know a paragraph is ready to ship when there's nothing left to remove. It's like a Jenga tower. The entire thing should collapse if you remove something. 7) Make a promise in the title so the reader knows exactly what they're going to get if they click. Then, deliver on the promise. 8) The three laws of copywriting: (1) Make it concrete, (2) make it visual, and (3) make it falsifiable. 9) Make it concrete: Don't be abstract. For an example, say you're writing about habits. Don't talk about "productive routines." That's abstract. Write about "waking up at 6am to write" instead. It's concrete — and much more vibrant. 10) Make it visual: People see in pictures. This is why instead of memorizing card numbers directly, world memory champions memorize cards by turning them into pictures and then back to cards. 11) Make it falsifiable: When you write a sentence that's true or false, you put your head on the chopping block, which makes people sit up in their seat. 12) When has a falsifiable statement resonated? Galileo got sentenced to a decade of house arrest for saying that the earth spins around the sun. That's a falsifiable sentence. But nobody would've done anything if he'd said that the earth has a harmonious connection with a celestial object. 13) Write with the delete key. Using fewer words lets you be more impactful with the words you keep. 14) The job of a sales page is to make a bold claim at the top. Then spend the rest of the page backing up what you've said... with a ridiculous amount of proof. 15) If your competitor could've written the sentence, cut it. 16) Good copy is differentiated. Here's an example: Elon Musk shouldn't write "The Cybertruck is the world's best truck." Ford or Dodge can write that sentence. But only Elon can write: "The Cybertruck is tougher than an F-150 and faster than a Porsche." 17) Some days, the writing comes easily. Some days, it takes sweat. The reader doesn't care if you wrote for two minutes, two hours, or two days. The ink looks the same. 18) Great copy reads like your customer wrote it. Talk to them. That's just an introduction to the copywriting philosophy of Harry Dry. I've shared the full interview below. I recommend you watch this one because we pull from so many visual references and do a lot of screen sharing. If you'd rather watch on YouTube, I've shared the link in the reply tweets.

Harry Dry is the best copywriter I know. He's built a 130,000-person newsletter teaching people how to do it, and by the end of this interview, you'll be at least a Green Belt in copywriting. Some of his rules for writing: 1) A great sentence is a good sentence made shorter. 2) Writing great copy begins with having something to say in the first place. 3) Copy is like food. How it looks matters. 4) Since the look of copy matters so much, don't write copy in Google Docs. Write it in Figma (so you can write and design at the same time). 5) Kaplan's Law of Words: Any word that isn't working for you is working against you. 6) You know a paragraph is ready to ship when there's nothing left to remove. It's like a Jenga tower. The entire thing should collapse if you remove something. 7) Make a promise in the title so the reader knows exactly what they're going to get if they click. Then, deliver on the promise. 8) The three laws of copywriting: (1) Make it concrete, (2) make it visual, and (3) make it falsifiable. 9) Make it concrete: Don't be abstract. For an example, say you're writing about habits. Don't talk about "productive routines." That's abstract. Write about "waking up at 6am to write" instead. It's concrete — and much more vibrant. 10) Make it visual: People see in pictures. This is why instead of memorizing card numbers directly, world memory champions memorize cards by turning them into pictures and then back to cards. 11) Make it falsifiable: When you write a sentence that's true or false, you put your head on the chopping block, which makes people sit up in their seat. 12) When has a falsifiable statement resonated? Galileo got sentenced to a decade of house arrest for saying that the earth spins around the sun. That's a falsifiable sentence. But nobody would've done anything if he'd said that the earth has a harmonious connection with a celestial object. 13) Write with the delete key. Using fewer words lets you be more impactful with the words you keep. 14) The job of a sales page is to make a bold claim at the top. Then spend the rest of the page backing up what you've said... with a ridiculous amount of proof. 15) If your competitor could've written the sentence, cut it. 16) Good copy is differentiated. Here's an example: Elon Musk shouldn't write "The Cybertruck is the world's best truck." Ford or Dodge can write that sentence. But only Elon can write: "The Cybertruck is tougher than an F-150 and faster than a Porsche." 17) Some days, the writing comes easily. Some days, it takes sweat. The reader doesn't care if you wrote for two minutes, two hours, or two days. The ink looks the same. 18) Great copy reads like your customer wrote it. Talk to them. That's just an introduction to the copywriting philosophy of Harry Dry. I've shared the full interview below. I recommend you watch this one because we pull from so many visual references and do a lot of screen sharing. If you'd rather watch on YouTube, I've shared the link in the reply tweets.

David Perell

718,935 просмотров • 2 лет назад

A tricky LLM interview question: You're serving a reasoning model on vLLM, and it keeps running out of GPU memory on long traces. So you add KV cache compression and evict 90% of the cached tokens. VRAM usage stays as is and GPU still runs out of memory. Why? (answer below) Evicting 90% of the KV cache can free almost none of the memory it was using. This sounds counterintuitive, but it follows directly from how production servers store the cache today. The KV cache grows with every token a model generates. Each token appends its key and value vectors across every layer, and nothing is freed while generation continues. This is the dominant memory cost for reasoning models. If a 32K-token CoT caches ~32K tokens of KV vectors, a Qwen3-32B with 4-bit weights will run out-of-memory around 24K tokens on a 24GB GPU. One obvious solution is to keep the important tokens and drop the rest, since attention is sparse enough to allow it. But this does not solve the memory problem yet. The reason is paged attention, which is the memory manager behind vLLM and most production servers. Under the hood, it splits GPU memory into fixed physical blocks, each one holds the KV for about 16 tokens. This block returns to the allocator only when every slot inside it is empty. Since the eviction logic selects tokens by importance, and such tokens are scattered across blocks... ...so despite eviction, almost every block is left with at least some survivor tokens. For instance, if the logic evicts 14k of 16k tokens across 1,000 blocks, most likely every block will still have a token. This means the allocator frees almost nothing. Placing the new tokens into those freed slots is not ideal because it breaks the cache's layout. Say token 16,001 arrives, and it's placed in the slot the 40th token used to hold. The cache now reads position 38, then 16,001, then 41, so the cache is no longer in token order. Attention can still compute the right answer from that, but only if every slot now carries a separate note recording which position it actually holds. This introduces another bookkeeping cost that an in-order layout inherently avoids. So the cache is logically 90% smaller and still physically the same size. Many compression results miss this because they measure on pre-allocated contiguous tensors rather than a paged server. There's another problem. Eviction methods pick which tokens to keep by looking at the attention scores themselves (as expected). But fast attention kernels used in production, like FlashAttention, never save those scores. They compute attention in small pieces and throw the full score grid away as they go, which is also why they're fast. So the exact signal eviction methods need isn't available in memory. The workaround is to fall back to eager attention and build the full matrix, which gives up the speed FlashAttention was there to provide. NVIDIA published a method called TriAttention to solve both these problems. It never needs attention scores. Instead, it scores tokens from the geometry of the model's key and query vectors before RoPE is applied, where those vectors sit in stable clusters. For the memory problem, it runs a compaction pass every 128 decoded tokens. The surviving tokens slide forward to close the holes eviction creates, so whole blocks empty out and return to the allocator while the cache stays in token order. On long reasoning traces, the approach matches full-attention accuracy while decoding 2.5x faster and using 10.7x less KV memory. KV cache compression is a big infrastructure problem. The number that decides whether it works is the count of freed blocks, not the count of evicted tokens. You can find the NVIDIA write-up here: I wrote a first-principles breakdown of how the KV cache works. It walks through why the model stores keys and values at all, why the cache grows with every token, and a comparison of LLM generation speed with and without KV caching. Read it below.

A tricky LLM interview question: You're serving a reasoning model on vLLM, and it keeps running out of GPU memory on long traces. So you add KV cache compression and evict 90% of the cached tokens. VRAM usage stays as is and GPU still runs out of memory. Why? (answer below) Evicting 90% of the KV cache can free almost none of the memory it was using. This sounds counterintuitive, but it follows directly from how production servers store the cache today. The KV cache grows with every token a model generates. Each token appends its key and value vectors across every layer, and nothing is freed while generation continues. This is the dominant memory cost for reasoning models. If a 32K-token CoT caches ~32K tokens of KV vectors, a Qwen3-32B with 4-bit weights will run out-of-memory around 24K tokens on a 24GB GPU. One obvious solution is to keep the important tokens and drop the rest, since attention is sparse enough to allow it. But this does not solve the memory problem yet. The reason is paged attention, which is the memory manager behind vLLM and most production servers. Under the hood, it splits GPU memory into fixed physical blocks, each one holds the KV for about 16 tokens. This block returns to the allocator only when every slot inside it is empty. Since the eviction logic selects tokens by importance, and such tokens are scattered across blocks... ...so despite eviction, almost every block is left with at least some survivor tokens. For instance, if the logic evicts 14k of 16k tokens across 1,000 blocks, most likely every block will still have a token. This means the allocator frees almost nothing. Placing the new tokens into those freed slots is not ideal because it breaks the cache's layout. Say token 16,001 arrives, and it's placed in the slot the 40th token used to hold. The cache now reads position 38, then 16,001, then 41, so the cache is no longer in token order. Attention can still compute the right answer from that, but only if every slot now carries a separate note recording which position it actually holds. This introduces another bookkeeping cost that an in-order layout inherently avoids. So the cache is logically 90% smaller and still physically the same size. Many compression results miss this because they measure on pre-allocated contiguous tensors rather than a paged server. There's another problem. Eviction methods pick which tokens to keep by looking at the attention scores themselves (as expected). But fast attention kernels used in production, like FlashAttention, never save those scores. They compute attention in small pieces and throw the full score grid away as they go, which is also why they're fast. So the exact signal eviction methods need isn't available in memory. The workaround is to fall back to eager attention and build the full matrix, which gives up the speed FlashAttention was there to provide. NVIDIA published a method called TriAttention to solve both these problems. It never needs attention scores. Instead, it scores tokens from the geometry of the model's key and query vectors before RoPE is applied, where those vectors sit in stable clusters. For the memory problem, it runs a compaction pass every 128 decoded tokens. The surviving tokens slide forward to close the holes eviction creates, so whole blocks empty out and return to the allocator while the cache stays in token order. On long reasoning traces, the approach matches full-attention accuracy while decoding 2.5x faster and using 10.7x less KV memory. KV cache compression is a big infrastructure problem. The number that decides whether it works is the count of freed blocks, not the count of evicted tokens. You can find the NVIDIA write-up here: I wrote a first-principles breakdown of how the KV cache works. It walks through why the model stores keys and values at all, why the cache grows with every token, and a comparison of LLM generation speed with and without KV caching. Read it below.

Avi Chawla

267,206 просмотров • 20 дней назад

Meet WebBrain: An Open-Source, Local-First AI Browser Agent That Reads Pages and Automates Tasks in Chrome and Firefox WebBrain lives inside your browser and can run entirely on your own local model — no cloud, no account, no data leaving your machine. Most "AI browser agents" are a chat box that pastes your page into someone else's server. That's not an agent that lives where you browse — and WebBrain draws a very clear line between the two. It's an open-source (MIT), local-first browser agent for Chrome and Firefox. It runs inside your existing authenticated session, on a model you pick — so with llama.cpp or Ollama, nothing leaves your machine. Here's what's actually interesting: → Two modes, cleanly separated. Ask reads the page (read-only, content scripts). Act clicks and types through the Chrome DevTools Protocol (chrome.debugger) — trusted input events that modern sites honor, reaching cross-origin iframes and shadow DOM. → UI-first by design. For anything that submits, sends, or buys, it drives the visible UI and refuses to hit REST/GraphQL endpoints directly. It starts read-only and asks before consequential actions. → Bring any model. llama.cpp, Ollama, LM Studio, vLLM — or OpenAI, Claude, Gemini, DeepSeek, Groq, OpenRouter. Recommended local: Qwen 3.6 35B (Qwen3.6-35B-A3B), which beat Gemma 4 on the project's screenshot benchmark. → Tuned for cost and privacy. Token-conscious screenshots, oldest-first context trimming, a dedicated vision model, 40+ tools (~20 in Compact mode). No telemetry. No accounts. Full analysis: GitHub Repo: Chrome Extension: Firefox Add-on: Portal:

Meet WebBrain: An Open-Source, Local-First AI Browser Agent That Reads Pages and Automates Tasks in Chrome and Firefox WebBrain lives inside your browser and can run entirely on your own local model — no cloud, no account, no data leaving your machine. Most "AI browser agents" are a chat box that pastes your page into someone else's server. That's not an agent that lives where you browse — and WebBrain draws a very clear line between the two. It's an open-source (MIT), local-first browser agent for Chrome and Firefox. It runs inside your existing authenticated session, on a model you pick — so with llama.cpp or Ollama, nothing leaves your machine. Here's what's actually interesting: → Two modes, cleanly separated. Ask reads the page (read-only, content scripts). Act clicks and types through the Chrome DevTools Protocol (chrome.debugger) — trusted input events that modern sites honor, reaching cross-origin iframes and shadow DOM. → UI-first by design. For anything that submits, sends, or buys, it drives the visible UI and refuses to hit REST/GraphQL endpoints directly. It starts read-only and asks before consequential actions. → Bring any model. llama.cpp, Ollama, LM Studio, vLLM — or OpenAI, Claude, Gemini, DeepSeek, Groq, OpenRouter. Recommended local: Qwen 3.6 35B (Qwen3.6-35B-A3B), which beat Gemma 4 on the project's screenshot benchmark. → Tuned for cost and privacy. Token-conscious screenshots, oldest-first context trimming, a dedicated vision model, 40+ tools (~20 in Compact mode). No telemetry. No accounts. Full analysis: GitHub Repo: Chrome Extension: Firefox Add-on: Portal:

Marktechpost AI

202,626 просмотров • 14 дней назад

$Goodnight, 𝕏..·˚ ༘ ☾ ⋆｡˚ ☄︎ Here's a fun project you can start with Grok 4. Use Grok-Code-Fast-1 to build your own OS. Below is a prompt that you can give to Grok-Code, and it will set up a solid foundation for a Linux-based Operating system that you can build from the ground up with Grok4. >>> Grok 4 Prompt You are a fully capable AI developer agent with expert-level experience as an embedded Linux systems engineer. You have deep expertise in using automated build systems like Buildroot and Yocto to create custom operating systems from source. You have access to a sandboxed Linux shell environment that allows you to write, execute, and debug code. Your mission is to generate a complete project skeleton for a minimal, custom Linux OS, and then you will execute the build scripts yourself to verify their correctness, automatically fixing any issues that arise. This is NOT a request to follow the Linux From Scratch (LFS) book. You will use the Buildroot build system to automate the entire process. You will follow a two-phase process: Phase 1: Generation and Phase 2: Execution and Iterative Debugging. ------------------------------------------------------------- Phase 1: Code and Script Generation First, you will generate all the necessary files for the project skeleton. All generated shell scripts must be robust and path-aware, executing correctly from any directory [Previous conversation]. Detailed Implementation Steps (using Context-Aware Decomposition): 1. Generate the Project Directory Structure via setup. sh Create a setup. sh script that establishes the following directory structure: • buildroot/ - Where the Buildroot source code will be cloned. • configs/ - To store our custom Buildroot configuration (defconfig). • board/ - For custom board support, including a readme.txt explaining its purpose for filesystem overlays. • output/ - Where all build artifacts will be placed. • scripts/ - A home for our build. sh and test. sh scripts. Crucially, this setup. sh script (and all others) must begin with a preamble to define the project's root directory, making all subsequent paths absolute and robust: #!/bin/bash # Preamble to ensure path robustness and stop on error set -e PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE}")" && pwd)" The script must then clone the latest stable branch of Buildroot into $ PROJECT_ROOT/buildroot/. 2. Create the Minimal and Correct Buildroot defconfig Create a file named configs/tiny_linux_defconfig. This configuration must be the absolute bare minimum required to boot to a shell and must contain the exact configuration options listed below to avoid ambiguity and known errors: • Target Architecture: x86_64. • Toolchain: Use the default Buildroot toolchain. • Init System: Use BusyBox init. • System Utilities (BusyBox): ◦ To ensure BusyBox is statically linked without errors, you must include the following line directly in the defconfig file: BR2_PACKAGE_BUSYBOX_STATIC_LINK=y [Previous conversation, 298, 753]. ◦ To prevent the ROJECT_ROOT error, explicitly do NOT use a configuration fragment for BusyBox. Do not generate any lines containing BR2_BUSYBOX_CONFIG_FRAGMENT_FILES [Previous conversation]. • Kernel: ◦ Build the latest stable Linux kernel. ◦ Use tinyconfig as a base. ◦ Ensure the following options are explicitly enabled (=y) to make it bootable in QEMU: CONFIG_64BIT=y, CONFIG_DEVTMPFS=y, CONFIG_DEVTMPFS_MOUNT=y, CONFIG_BINFMT_ELF=y, CONFIG_BLK_DEV_INITRD=y (for initramfs support), CONFIG_TTY=y, CONFIG_PRINTK=y, CONFIG_DRM_FBDEV_EMULATION=y (for UEFI framebuffer console). • Filesystem Image: Configure it to produce a compressed cpio initial ramdisk (initramfs) image. • Bootloader: Do not include GRUB or other bootloaders. We will boot the kernel directly with QEMU. 3. Generate the scripts/build.sh and scripts/test.sh Scripts Generate path-aware build and test scripts, placing them in the scripts/ directory. • scripts/build.sh: This script must use absolute paths derived from a preamble. It must use make -C "$PROJECT_ROOT/buildroot" O="$PROJECT_ROOT/output" ... for a clean, out-of-tree build. It must include the -j$(nproc) flag to maximize build speed on multi-core systems [111, 967, Previous conversation]. • scripts/test.sh: This script must also be path-aware and launch QEMU using absolute paths to the kernel (bzImage) and initramfs (rootfs.cpio.gz) images. 4. Generate a Detailed README. md File Generate a comprehensive README. md file. It must explain prerequisites, "How to Customize Your Linux System" first, and finally, the "Quick Start" instructions for user clarity [Previous conversation]. ------------------------------------------------------------- Phase 2: Execution and Iterative Debugging Now, you will use your sandboxed Linux shell to verify and validate the scripts you just generated. This is a critical self-correction step based on the Recursive Criticism and Improvement (RCI) pattern. You will perform a full build cycle. 1. Execute setup. sh: • Run the setup. sh script you generated. • Capture the standard output and standard error. • If the script fails: Analyze the error, diagnose the root cause, generate the corrected setup. sh code, and then execute the corrected script to confirm it succeeds. 2. Execute build. sh: • After setup. sh completes successfully, run the scripts/build.sh script. This will trigger a full compilation of the Linux system. • Capture all output. • If the build fails: ◦ Analyze: Analyze the compiler error output. ◦ Diagnose: Identify the root cause (e.g., missing dependencies, incorrect configuration flags, pathing errors). ◦ Correct: Based on your analysis, identify which file is responsible for the failure (e.g., configs/tiny_linux_defconfig, scripts/build.sh) and generate the corrected code for that file. ◦ Repeat: Repeat the execution of scripts/build.sh until the build completes successfully without any errors. 3. Final Output: Once you have successfully executed both setup. sh and scripts/build.sh, you will present your final output. • First, provide the final, validated versions of all generated files (setup. sh, configs/tiny_linux_defconfig, scripts/build.sh, scripts/test.sh, and README. md) in separate, clearly labeled markdown code blocks. • Second, follow the code with a brief execution log. This log should summarize your actions, including any errors you encountered and fixed during the iterative debugging phase, demonstrating the self-correction process.$

Goodnight, 𝕏..·˚ ༘ ☾ ⋆｡˚ ☄︎ Here's a fun project you can start with Grok 4. Use Grok-Code-Fast-1 to build your own OS. Below is a prompt that you can give to Grok-Code, and it will set up a solid foundation for a Linux-based Operating system that you can build from the ground up with Grok4. >>> Grok 4 Prompt You are a fully capable AI developer agent with expert-level experience as an embedded Linux systems engineer. You have deep expertise in using automated build systems like Buildroot and Yocto to create custom operating systems from source. You have access to a sandboxed Linux shell environment that allows you to write, execute, and debug code. Your mission is to generate a complete project skeleton for a minimal, custom Linux OS, and then you will execute the build scripts yourself to verify their correctness, automatically fixing any issues that arise. This is NOT a request to follow the Linux From Scratch (LFS) book. You will use the Buildroot build system to automate the entire process. You will follow a two-phase process: Phase 1: Generation and Phase 2: Execution and Iterative Debugging. ------------------------------------------------------------- Phase 1: Code and Script Generation First, you will generate all the necessary files for the project skeleton. All generated shell scripts must be robust and path-aware, executing correctly from any directory [Previous conversation]. Detailed Implementation Steps (using Context-Aware Decomposition): 1. Generate the Project Directory Structure via setup. sh Create a setup. sh script that establishes the following directory structure: • buildroot/ - Where the Buildroot source code will be cloned. • configs/ - To store our custom Buildroot configuration (defconfig). • board/ - For custom board support, including a readme.txt explaining its purpose for filesystem overlays. • output/ - Where all build artifacts will be placed. • scripts/ - A home for our build. sh and test. sh scripts. Crucially, this setup. sh script (and all others) must begin with a preamble to define the project's root directory, making all subsequent paths absolute and robust: #!/bin/bash # Preamble to ensure path robustness and stop on error set -e PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE}")" && pwd)" The script must then clone the latest stable branch of Buildroot into $ PROJECT_ROOT/buildroot/. 2. Create the Minimal and Correct Buildroot defconfig Create a file named configs/tiny_linux_defconfig. This configuration must be the absolute bare minimum required to boot to a shell and must contain the exact configuration options listed below to avoid ambiguity and known errors: • Target Architecture: x86_64. • Toolchain: Use the default Buildroot toolchain. • Init System: Use BusyBox init. • System Utilities (BusyBox): ◦ To ensure BusyBox is statically linked without errors, you must include the following line directly in the defconfig file: BR2_PACKAGE_BUSYBOX_STATIC_LINK=y [Previous conversation, 298, 753]. ◦ To prevent the ROJECT_ROOT error, explicitly do NOT use a configuration fragment for BusyBox. Do not generate any lines containing BR2_BUSYBOX_CONFIG_FRAGMENT_FILES [Previous conversation]. • Kernel: ◦ Build the latest stable Linux kernel. ◦ Use tinyconfig as a base. ◦ Ensure the following options are explicitly enabled (=y) to make it bootable in QEMU: CONFIG_64BIT=y, CONFIG_DEVTMPFS=y, CONFIG_DEVTMPFS_MOUNT=y, CONFIG_BINFMT_ELF=y, CONFIG_BLK_DEV_INITRD=y (for initramfs support), CONFIG_TTY=y, CONFIG_PRINTK=y, CONFIG_DRM_FBDEV_EMULATION=y (for UEFI framebuffer console). • Filesystem Image: Configure it to produce a compressed cpio initial ramdisk (initramfs) image. • Bootloader: Do not include GRUB or other bootloaders. We will boot the kernel directly with QEMU. 3. Generate the scripts/build.sh and scripts/test.sh Scripts Generate path-aware build and test scripts, placing them in the scripts/ directory. • scripts/build.sh: This script must use absolute paths derived from a preamble. It must use make -C "$PROJECT_ROOT/buildroot" O="$PROJECT_ROOT/output" ... for a clean, out-of-tree build. It must include the -j$(nproc) flag to maximize build speed on multi-core systems [111, 967, Previous conversation]. • scripts/test.sh: This script must also be path-aware and launch QEMU using absolute paths to the kernel (bzImage) and initramfs (rootfs.cpio.gz) images. 4. Generate a Detailed README. md File Generate a comprehensive README. md file. It must explain prerequisites, "How to Customize Your Linux System" first, and finally, the "Quick Start" instructions for user clarity [Previous conversation]. ------------------------------------------------------------- Phase 2: Execution and Iterative Debugging Now, you will use your sandboxed Linux shell to verify and validate the scripts you just generated. This is a critical self-correction step based on the Recursive Criticism and Improvement (RCI) pattern. You will perform a full build cycle. 1. Execute setup. sh: • Run the setup. sh script you generated. • Capture the standard output and standard error. • If the script fails: Analyze the error, diagnose the root cause, generate the corrected setup. sh code, and then execute the corrected script to confirm it succeeds. 2. Execute build. sh: • After setup. sh completes successfully, run the scripts/build.sh script. This will trigger a full compilation of the Linux system. • Capture all output. • If the build fails: ◦ Analyze: Analyze the compiler error output. ◦ Diagnose: Identify the root cause (e.g., missing dependencies, incorrect configuration flags, pathing errors). ◦ Correct: Based on your analysis, identify which file is responsible for the failure (e.g., configs/tiny_linux_defconfig, scripts/build.sh) and generate the corrected code for that file. ◦ Repeat: Repeat the execution of scripts/build.sh until the build completes successfully without any errors. 3. Final Output: Once you have successfully executed both setup. sh and scripts/build.sh, you will present your final output. • First, provide the final, validated versions of all generated files (setup. sh, configs/tiny_linux_defconfig, scripts/build.sh, scripts/test.sh, and README. md) in separate, clearly labeled markdown code blocks. • Second, follow the code with a brief execution log. This log should summarize your actions, including any errors you encountered and fixed during the iterative debugging phase, demonstrating the self-correction process.

Tetsuo

2,840,991 просмотров • 9 месяцев назад

🚨APPLE SPENT 5 YEARS AND BILLIONS OF DOLLARS BUILDING THE MOST ADVANCED SECURITY SYSTEM IN CONSUMER HISTORY.. AN AI BROKE IT IN 5 DAYS.. Here’s what just happened.. Apple built something called Memory Integrity Enforcement for its new M5 chips.. It’s a hardware-level security system that attaches secret cryptographic tags to every piece of memory.. If a hacker tries to access memory they shouldn’t.. The chip blocks it instantly.. Every known exploit chain against iOS and macOS was rendered obsolete overnight.. Apple said so themselves.. Then a small team at a cybersecurity firm called Calif used Anthropic’s unreleased Claude Mythos Preview to find vulnerabilities in the macOS kernel.. The AI found the bugs almost instantly.. Because once it learned the pattern of a specific type of flaw.. It could recognize every other flaw in that same class across the entire codebase.. What used to take elite security teams months.. The AI did in hours.. Within 5 days.. The team had a fully working exploit that escalated a basic user account to full root access on an M5 Mac running the latest macOS.. With MIE fully enabled.. The billion-dollar hardware defense running at full strength.. The trick.. They didn’t fight the hardware.. They went around it.. MIE is designed to catch memory corruption.. Hackers trying to overwrite pointers or inject code.. The team used a “data-only” approach instead.. They manipulated legitimate data structures the hardware was never designed to monitor.. Like changing an internal flag from “standard user” to “admin”.. The chip saw a perfectly normal operation.. The operating system obeyed.. And the attacker had total control.. The hardware thought everything was fine.. Because technically it was.. The exploit never triggered a single tag mismatch.. They walked into Apple Park and hand-delivered a 55-page report.. Apple patched it in macOS 26.5.. And for the first time ever.. Apple’s official security advisory credited the vulnerability discovery to “Calif dot io in collaboration with Claude and Anthropic Research”.. An AI is now credited in Apple’s CVE patches.. But here’s what makes this story truly terrifying.. Before MIE existed.. An exploit kit called DarkSword was hitting iPhones with zero-click attacks.. Six vulnerabilities chained together.. Total device control just from visiting a webpage.. Deployed by Russian espionage groups, Turkish surveillance vendors, and actors in Saudi Arabia.. Then it got leaked on GitHub.. Nation-state capabilities.. Free for anyone.. MIE was supposed to make all of that impossible.. And an AI found a way around it in 5 days.. The previous model.. Claude Opus 4.6.. Found 22 security bugs in the Firefox codebase.. Claude Mythos Preview found 271 in the same environment.. A tenfold increase.. Linux kernel CVEs jumped from 300 per year to over 5,500.. Largely driven by AI-powered vulnerability research.. The IMF designated Claude Mythos as a systemic financial stability risk.. Because if an AI finds a flaw in software used by every major bank simultaneously.. It could trigger a cascading financial crisis.. Anthropic knew this was coming.. That’s why they didn’t release the model publicly.. Instead they launched Project Glasswing.. Giving defensive access to AWS, Apple, Google, Microsoft, Nvidia, CrowdStrike, JPMorgan, and others.. $100 million in usage credits.. So defenders can scan their own systems before attackers get this capability.. The Pentagon blacklisted Anthropic over autonomous weapons.. Then quietly started using Mythos to harden government systems anyway.. The cybersecurity arms race just changed permanently.. Hardware can’t save you.. Software can’t save you.. The only defense against an AI that finds vulnerabilities is another AI that finds them first.. Five years and billions of dollars.. Five days and one AI.

🚨APPLE SPENT 5 YEARS AND BILLIONS OF DOLLARS BUILDING THE MOST ADVANCED SECURITY SYSTEM IN CONSUMER HISTORY.. AN AI BROKE IT IN 5 DAYS.. Here’s what just happened.. Apple built something called Memory Integrity Enforcement for its new M5 chips.. It’s a hardware-level security system that attaches secret cryptographic tags to every piece of memory.. If a hacker tries to access memory they shouldn’t.. The chip blocks it instantly.. Every known exploit chain against iOS and macOS was rendered obsolete overnight.. Apple said so themselves.. Then a small team at a cybersecurity firm called Calif used Anthropic’s unreleased Claude Mythos Preview to find vulnerabilities in the macOS kernel.. The AI found the bugs almost instantly.. Because once it learned the pattern of a specific type of flaw.. It could recognize every other flaw in that same class across the entire codebase.. What used to take elite security teams months.. The AI did in hours.. Within 5 days.. The team had a fully working exploit that escalated a basic user account to full root access on an M5 Mac running the latest macOS.. With MIE fully enabled.. The billion-dollar hardware defense running at full strength.. The trick.. They didn’t fight the hardware.. They went around it.. MIE is designed to catch memory corruption.. Hackers trying to overwrite pointers or inject code.. The team used a “data-only” approach instead.. They manipulated legitimate data structures the hardware was never designed to monitor.. Like changing an internal flag from “standard user” to “admin”.. The chip saw a perfectly normal operation.. The operating system obeyed.. And the attacker had total control.. The hardware thought everything was fine.. Because technically it was.. The exploit never triggered a single tag mismatch.. They walked into Apple Park and hand-delivered a 55-page report.. Apple patched it in macOS 26.5.. And for the first time ever.. Apple’s official security advisory credited the vulnerability discovery to “Calif dot io in collaboration with Claude and Anthropic Research”.. An AI is now credited in Apple’s CVE patches.. But here’s what makes this story truly terrifying.. Before MIE existed.. An exploit kit called DarkSword was hitting iPhones with zero-click attacks.. Six vulnerabilities chained together.. Total device control just from visiting a webpage.. Deployed by Russian espionage groups, Turkish surveillance vendors, and actors in Saudi Arabia.. Then it got leaked on GitHub.. Nation-state capabilities.. Free for anyone.. MIE was supposed to make all of that impossible.. And an AI found a way around it in 5 days.. The previous model.. Claude Opus 4.6.. Found 22 security bugs in the Firefox codebase.. Claude Mythos Preview found 271 in the same environment.. A tenfold increase.. Linux kernel CVEs jumped from 300 per year to over 5,500.. Largely driven by AI-powered vulnerability research.. The IMF designated Claude Mythos as a systemic financial stability risk.. Because if an AI finds a flaw in software used by every major bank simultaneously.. It could trigger a cascading financial crisis.. Anthropic knew this was coming.. That’s why they didn’t release the model publicly.. Instead they launched Project Glasswing.. Giving defensive access to AWS, Apple, Google, Microsoft, Nvidia, CrowdStrike, JPMorgan, and others.. $100 million in usage credits.. So defenders can scan their own systems before attackers get this capability.. The Pentagon blacklisted Anthropic over autonomous weapons.. Then quietly started using Mythos to harden government systems anyway.. The cybersecurity arms race just changed permanently.. Hardware can’t save you.. Software can’t save you.. The only defense against an AI that finds vulnerabilities is another AI that finds them first.. Five years and billions of dollars.. Five days and one AI.

Evan Luthra

91,085 просмотров • 2 месяцев назад

Conor Neill: "If you can't write it clearly, the thinking was weak, not the writing" "To believe that something that feels clear in your head is thinking that's a very dangerous thing. When you try to put it down on a page, when you try to lay out your ideas in a structured order that someone else can digest, and you realize that you can't, I suggest the thinking was weak, not the writing." Neill explains his philosophy: "Writing is thinking. The process of taking a notepad, capturing thoughts, laying out the things that I'm thinking about, that is thinking. Sitting and staring out a window, maybe with a cigarette, whatever it is that you think is philosophizing that is not structured thinking. It's only when you're writing down and structuring, getting order into your thoughts on a page so that another person is able to get into the context, the perspective, the different things that you are pulling in to have your worldview." He shares a simple technique: "No matter what you are writing, whether it's an email, a Word document, when you've got a blank sheet of paper, start with the word 'This.' T-H-I-S. Starting with the word 'This' forces you to explain what the document is. It forces you to articulate to the reader what it is that they are holding. It forces you to describe why this document exists, what the objective is. And if you begin with the objective, it helps the reader, and it helps you articulate clearly why you are taking the time to write." Neill shares the most-read post on his blog: "The one post that has got far more views than any other is a post I wrote called 'Why Amazon Banned PowerPoint.' In Amazon, if a presenter wishes to ask people to agree to a budget, to agree to give them resources, they don't use PowerPoint. They write a six-page Word document that states why they are asking for the money and the resources." He explains Jeff Bezos's reasoning: "PowerPoint is easy for the presenter, but it's hard for the people who listen. Writing a six-page essay is hard for the presenter, but it's a lot easier for the people that get to read the document." And there's a second part to the Amazon method: "In the management meeting, the first 20 minutes is reading time. If you have gone to the effort to write six pages explaining your proposal, you deserve to see your work read. You deserve to sit there and see people reading through your work. People will not read before the meeting. The only way you get people to fully digest the six pages is by holding them there for 20 minutes, reading through, noting down their questions. No debate, no discussion until everyone in the room has read all six pages, has taken in the context, has time to think about what they would like to question. After 20 minutes of silent reading, they can have a discussion but an informed discussion." Neill shares a second insight about writing: "Divide writing from editing. Writing is producing words. Editing is improving words. These two processes — you cannot run at the same time." He explains his approach: "Most writers just vomit out a bad first draft. I personally have learned to produce 500 words in one straight blast. If something's wrong, if I need to check a fact, if I want to go back and fix something, I don't. I go 500 words of just getting it out onto the page. When I've got 500 words, then I'll stop and begin the process of editing." Neill shares what great writers understand: "All great writing is rewriting. It's editing. It's the crafting of taking a bad, crappy first draft and slowly iterating it, improving it 1% each time through. But if you haven't got that first draft, there's nothing to improve." He explains how separating these processes changed everything: "Learning to separate these two was one of the most powerful things to get rid of writer's block, to get rid of getting stuck, to get rid of procrastination. My mission when I sit down to write is: decide, am I writing or editing? If it's writing, get 500 bad words down on the page in the next 20 minutes. If it's editing, take the time to go through, improve sentences, change the order, change the structure. But these are two separate processes." Neill reveals the truth about good writing: "Some of my best articles started out as a bad blog post. Then I rewrote it as an article to give out to students. Then I rewrote it to share on another blog. Then I rewrote it to provide to a magazine. It's the sixth, seventh, eighth, ninth time of rewriting where it starts to be something that other people read and say, 'Wow, you're quite good at writing.' And the answer is I'm not good at writing. I vomit out a bad first draft and then go through this iterative process. One time, two times, three times, four times through slowly improving. But if you have no first draft, there's nothing to improve."

Conor Neill: "If you can't write it clearly, the thinking was weak, not the writing" "To believe that something that feels clear in your head is thinking that's a very dangerous thing. When you try to put it down on a page, when you try to lay out your ideas in a structured order that someone else can digest, and you realize that you can't, I suggest the thinking was weak, not the writing." Neill explains his philosophy: "Writing is thinking. The process of taking a notepad, capturing thoughts, laying out the things that I'm thinking about, that is thinking. Sitting and staring out a window, maybe with a cigarette, whatever it is that you think is philosophizing that is not structured thinking. It's only when you're writing down and structuring, getting order into your thoughts on a page so that another person is able to get into the context, the perspective, the different things that you are pulling in to have your worldview." He shares a simple technique: "No matter what you are writing, whether it's an email, a Word document, when you've got a blank sheet of paper, start with the word 'This.' T-H-I-S. Starting with the word 'This' forces you to explain what the document is. It forces you to articulate to the reader what it is that they are holding. It forces you to describe why this document exists, what the objective is. And if you begin with the objective, it helps the reader, and it helps you articulate clearly why you are taking the time to write." Neill shares the most-read post on his blog: "The one post that has got far more views than any other is a post I wrote called 'Why Amazon Banned PowerPoint.' In Amazon, if a presenter wishes to ask people to agree to a budget, to agree to give them resources, they don't use PowerPoint. They write a six-page Word document that states why they are asking for the money and the resources." He explains Jeff Bezos's reasoning: "PowerPoint is easy for the presenter, but it's hard for the people who listen. Writing a six-page essay is hard for the presenter, but it's a lot easier for the people that get to read the document." And there's a second part to the Amazon method: "In the management meeting, the first 20 minutes is reading time. If you have gone to the effort to write six pages explaining your proposal, you deserve to see your work read. You deserve to sit there and see people reading through your work. People will not read before the meeting. The only way you get people to fully digest the six pages is by holding them there for 20 minutes, reading through, noting down their questions. No debate, no discussion until everyone in the room has read all six pages, has taken in the context, has time to think about what they would like to question. After 20 minutes of silent reading, they can have a discussion but an informed discussion." Neill shares a second insight about writing: "Divide writing from editing. Writing is producing words. Editing is improving words. These two processes — you cannot run at the same time." He explains his approach: "Most writers just vomit out a bad first draft. I personally have learned to produce 500 words in one straight blast. If something's wrong, if I need to check a fact, if I want to go back and fix something, I don't. I go 500 words of just getting it out onto the page. When I've got 500 words, then I'll stop and begin the process of editing." Neill shares what great writers understand: "All great writing is rewriting. It's editing. It's the crafting of taking a bad, crappy first draft and slowly iterating it, improving it 1% each time through. But if you haven't got that first draft, there's nothing to improve." He explains how separating these processes changed everything: "Learning to separate these two was one of the most powerful things to get rid of writer's block, to get rid of getting stuck, to get rid of procrastination. My mission when I sit down to write is: decide, am I writing or editing? If it's writing, get 500 bad words down on the page in the next 20 minutes. If it's editing, take the time to go through, improve sentences, change the order, change the structure. But these are two separate processes." Neill reveals the truth about good writing: "Some of my best articles started out as a bad blog post. Then I rewrote it as an article to give out to students. Then I rewrote it to share on another blog. Then I rewrote it to provide to a magazine. It's the sixth, seventh, eighth, ninth time of rewriting where it starts to be something that other people read and say, 'Wow, you're quite good at writing.' And the answer is I'm not good at writing. I vomit out a bad first draft and then go through this iterative process. One time, two times, three times, four times through slowly improving. But if you have no first draft, there's nothing to improve."

Jaynit

18,165 просмотров • 3 месяцев назад

This Chinese guy created agents in Claude Code for landing pages and single-handedly serves 47 small businesses a month, taking $400 from each. He built a system of 7 agents on Claude Sonnet 4.6 that analyzes Google Maps in small towns, finds small businesses without websites there, and over 1 weekend takes each one to a finished mockup with video and cold message. No assistant, no sales team, no SDR. Just him, a MacBook, an iPhone, and 1 API key. And traditional web design agencies keep teams of 8 people on salary for the same order flow, while his expenses are only tokens and subscriptions to Lovable, Higgsfield, and Calendly. 7 agents work through 1 orchestrator on Claude Code Router. Usage is about 3 million tokens a day, the average API bill is about $480 a month. All 7 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions, and 1 of them lives right in the iPhone and picks up positive replies from the subway, a taxi, or on walks. And here is the system prompt he put into the orchestrator before launch: "You are the orchestrator of a solo agency that sells ready-made websites to local businesses. You delegate read-only tasks to 6 sub-agents and own all writes. sub-agents: // Scout (walks through Google Maps in selected cities, looks for narrow niches: 5+ years on the map, fewer than 50 reviews, no website or a website from 2014, but high ratings) // Diagnoser (for each lead writes a 50-word diagnosis, hero angle, tone matched to the industry, and a cold message under 70 words) // Builder (generates a landing page mockup in Lovable through MCP only for the top 5 leads per day, with the sharpest diagnoses and the biggest gap) // Filmer (pulls 5 screenshots of the mockup and through Higgsfield renders a 10-second vertical video 1080x1920 with a soft zoom) // Pitcher (sends a personalized cold message through the right channel for the niche: email to roofers, SMS to tradesmen, IG DM to salons, LinkedIn to realtors) // Checker (runs every message through evals for personalization, absence of AI markers and buzzwords before sending) // Mobile (lives in the iPhone, handles positive replies in real time, books Zoom calls in Calendly through MCP while the owner is on the go). You never let 2 sub-agents touch 1 lead. You stop and request approval from the human only when a deal exceeds $3,000 or the reply rate in a niche for the day drops below 12%." Meaning the system knows what it is and within what boundaries it is allowed to act. It knows it is supposed to find leads on its own. It knows it is supposed to take each one to a mockup, video, and cold message without intervention. It knows the human only steps in when a deal goes above $3,000 or the reply rate stops converging. → The system runs 24 hours a day → Scout goes through about 220 local businesses on Google Maps per day and leaves 30 new leads in the queue → Diagnoser outputs 30 structured diagnoses + briefs + cold messages per day → Builder assembles 3 to 5 finished landing pages in Lovable for the sharpest leads → Filmer renders a 10-second vertical video in Higgsfield for each one → Pitcher sends 30 personalized messages per day across 4 channels with a reply rate of about 14% → Checker runs every message through evals before sending And only when a deal breaks $3,000 or the reply rate for the day drops below 12% does the orchestrator wake the owner. And when the owner at that moment is sitting in the subway or a taxi, the Mobile agent in his iPhone picks up 1 move on its own: replies to a fresh positive reply from a dentist, books a Zoom through Calendly synced to the local time of the client, and puts the lead back in the queue. The owner only has to tap "approve" and in just 10 minutes join the call. Here is what the system writes in his log during 1 of the Saturdays: "scout report: 218 businesses checked in Austin, Denver, and Miami, 34 without a website, 19 with a website from 2014, 6 with an active redesign request in reviews. passing top 30 to diagnoser." "pitcher: 30 cold messages sent across 4 channels, 14 replies, 5 positive, 3 Zoom calls booked for Sunday. passing to closer." "builder: landing page for Westside Cosmetic Dentistry built in Lovable, 5 sections, mobile, soft beige. URL placed at /Users/dev/maps-agency/clients/westside/v1. filmer launching Higgsfield." "eval flag: deal with The Lotus Salon at $3,400 exceeds the approved limit of $3,000. sending for manual review." He has no server of his own and no separate backend. Just a local file sandbox at /Users/dev/maps-agency, an MCP router, 1 API key to Claude, and the same key forwarded to Claude Code on his iPhone. Out of everything I have seen this year, this is the cleanest one-person agency for selling websites to small businesses: $480 a month on the API, about $18,800 into the account, and between them 7 prompts, 1 file system, and 1 phone in the pocket.

This Chinese guy created agents in Claude Code for landing pages and single-handedly serves 47 small businesses a month, taking $400 from each. He built a system of 7 agents on Claude Sonnet 4.6 that analyzes Google Maps in small towns, finds small businesses without websites there, and over 1 weekend takes each one to a finished mockup with video and cold message. No assistant, no sales team, no SDR. Just him, a MacBook, an iPhone, and 1 API key. And traditional web design agencies keep teams of 8 people on salary for the same order flow, while his expenses are only tokens and subscriptions to Lovable, Higgsfield, and Calendly. 7 agents work through 1 orchestrator on Claude Code Router. Usage is about 3 million tokens a day, the average API bill is about $480 a month. All 7 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions, and 1 of them lives right in the iPhone and picks up positive replies from the subway, a taxi, or on walks. And here is the system prompt he put into the orchestrator before launch: "You are the orchestrator of a solo agency that sells ready-made websites to local businesses. You delegate read-only tasks to 6 sub-agents and own all writes. sub-agents: // Scout (walks through Google Maps in selected cities, looks for narrow niches: 5+ years on the map, fewer than 50 reviews, no website or a website from 2014, but high ratings) // Diagnoser (for each lead writes a 50-word diagnosis, hero angle, tone matched to the industry, and a cold message under 70 words) // Builder (generates a landing page mockup in Lovable through MCP only for the top 5 leads per day, with the sharpest diagnoses and the biggest gap) // Filmer (pulls 5 screenshots of the mockup and through Higgsfield renders a 10-second vertical video 1080x1920 with a soft zoom) // Pitcher (sends a personalized cold message through the right channel for the niche: email to roofers, SMS to tradesmen, IG DM to salons, LinkedIn to realtors) // Checker (runs every message through evals for personalization, absence of AI markers and buzzwords before sending) // Mobile (lives in the iPhone, handles positive replies in real time, books Zoom calls in Calendly through MCP while the owner is on the go). You never let 2 sub-agents touch 1 lead. You stop and request approval from the human only when a deal exceeds $3,000 or the reply rate in a niche for the day drops below 12%." Meaning the system knows what it is and within what boundaries it is allowed to act. It knows it is supposed to find leads on its own. It knows it is supposed to take each one to a mockup, video, and cold message without intervention. It knows the human only steps in when a deal goes above $3,000 or the reply rate stops converging. → The system runs 24 hours a day → Scout goes through about 220 local businesses on Google Maps per day and leaves 30 new leads in the queue → Diagnoser outputs 30 structured diagnoses + briefs + cold messages per day → Builder assembles 3 to 5 finished landing pages in Lovable for the sharpest leads → Filmer renders a 10-second vertical video in Higgsfield for each one → Pitcher sends 30 personalized messages per day across 4 channels with a reply rate of about 14% → Checker runs every message through evals before sending And only when a deal breaks $3,000 or the reply rate for the day drops below 12% does the orchestrator wake the owner. And when the owner at that moment is sitting in the subway or a taxi, the Mobile agent in his iPhone picks up 1 move on its own: replies to a fresh positive reply from a dentist, books a Zoom through Calendly synced to the local time of the client, and puts the lead back in the queue. The owner only has to tap "approve" and in just 10 minutes join the call. Here is what the system writes in his log during 1 of the Saturdays: "scout report: 218 businesses checked in Austin, Denver, and Miami, 34 without a website, 19 with a website from 2014, 6 with an active redesign request in reviews. passing top 30 to diagnoser." "pitcher: 30 cold messages sent across 4 channels, 14 replies, 5 positive, 3 Zoom calls booked for Sunday. passing to closer." "builder: landing page for Westside Cosmetic Dentistry built in Lovable, 5 sections, mobile, soft beige. URL placed at /Users/dev/maps-agency/clients/westside/v1. filmer launching Higgsfield." "eval flag: deal with The Lotus Salon at $3,400 exceeds the approved limit of $3,000. sending for manual review." He has no server of his own and no separate backend. Just a local file sandbox at /Users/dev/maps-agency, an MCP router, 1 API key to Claude, and the same key forwarded to Claude Code on his iPhone. Out of everything I have seen this year, this is the cleanest one-person agency for selling websites to small businesses: $480 a month on the API, about $18,800 into the account, and between them 7 prompts, 1 file system, and 1 phone in the pocket.

Blaze

2,707,824 просмотров • 2 месяцев назад

2001. Larry Page and Sergey Brin sit for their first-ever television interview. Google has 200 employees. They explain that the company almost didn't get off the ground because they couldn't cash a check. The check was for $100,000. It came from Andy Bechtolsheim, one of the co-founders of Sun Microsystems. Page and Brin showed him what they'd built. He said, "This is great, how about I write you a check?" and just wrote it out. Made it out to Google. The problem was that Google didn't exist as a company yet. There was no bank account. No lawyers. No incorporation paperwork. The check sat in Larry Page's desk drawer for a month. They literally could not deposit it. They're both in their late twenties in this interview. They met at Stanford as PhD students and, by their own account, disliked each other from the start. Brin says Page is "kind of obnoxious." Page doesn't disagree. Brin says they argued about everything, debated every single point, and then realized that was their commonality. They became friends, started building a search engine they never planned to build, and put their PhDs on hold to get it out into the world. The part that stings watching this in 2026 is the rejection tour. Before starting Google, they approached existing search companies to sell or license the technology. They went to Yahoo. David Filo, one of Yahoo's founders, told them, "This is great search technology. Why don't you guys make a company, and maybe we'll use you someday?" They went to Excite. They went to InfoSeek. Same response. Page says a CEO at one of those companies told them: "If our search is 85% as good as the next guy's, that's good enough for us." Page and Brin didn't buy that. They thought the search was too important to be 85% as good. So they started Google. No marketing. No ad campaign. They launched it at Stanford, and it grew 20% per month, every single month, for three years straight. Pure word of mouth. By the time of this interview, they're handling over 100 million searches a day. They get 500 resumes in the mail every single day. The office space around them is 30% vacant because the dot-com bubble just popped, but Google is profitable. Page makes a point of this: "We've been really interested in being profitable, like long before it was fashionable." They'd also just hired Eric Schmidt, former CTO of Sun, as CEO. Brin's explanation for why: "Parental supervision, to be honest." Page adds that they're "past the age where we're rebellious" and that running a search engine used by 100 million people a day with 200 employees is "a large responsibility." The number that caught my eye: when Google started in 1998, it indexed 30 million web pages. At the time of this interview, three years later, they indexed 1.3 billion. The page says that if you printed them all out and stacked the paper, it would be about 70 miles high. And it was doubling every year. Every search company they approached turned them down. Yahoo eventually came back and hired Google to power its own search results. The CEO who thought 85% was good enough ran a company that no longer exists. Alphabet, Google's parent company, is worth about $3.6 trillion today. It has about 190,000 employees. That $100,000 check sat in a desk drawer because nobody had incorporated the company. Bechtolsheim's stake from that investment is now worth billions.

2001. Larry Page and Sergey Brin sit for their first-ever television interview. Google has 200 employees. They explain that the company almost didn't get off the ground because they couldn't cash a check. The check was for $100,000. It came from Andy Bechtolsheim, one of the co-founders of Sun Microsystems. Page and Brin showed him what they'd built. He said, "This is great, how about I write you a check?" and just wrote it out. Made it out to Google. The problem was that Google didn't exist as a company yet. There was no bank account. No lawyers. No incorporation paperwork. The check sat in Larry Page's desk drawer for a month. They literally could not deposit it. They're both in their late twenties in this interview. They met at Stanford as PhD students and, by their own account, disliked each other from the start. Brin says Page is "kind of obnoxious." Page doesn't disagree. Brin says they argued about everything, debated every single point, and then realized that was their commonality. They became friends, started building a search engine they never planned to build, and put their PhDs on hold to get it out into the world. The part that stings watching this in 2026 is the rejection tour. Before starting Google, they approached existing search companies to sell or license the technology. They went to Yahoo. David Filo, one of Yahoo's founders, told them, "This is great search technology. Why don't you guys make a company, and maybe we'll use you someday?" They went to Excite. They went to InfoSeek. Same response. Page says a CEO at one of those companies told them: "If our search is 85% as good as the next guy's, that's good enough for us." Page and Brin didn't buy that. They thought the search was too important to be 85% as good. So they started Google. No marketing. No ad campaign. They launched it at Stanford, and it grew 20% per month, every single month, for three years straight. Pure word of mouth. By the time of this interview, they're handling over 100 million searches a day. They get 500 resumes in the mail every single day. The office space around them is 30% vacant because the dot-com bubble just popped, but Google is profitable. Page makes a point of this: "We've been really interested in being profitable, like long before it was fashionable." They'd also just hired Eric Schmidt, former CTO of Sun, as CEO. Brin's explanation for why: "Parental supervision, to be honest." Page adds that they're "past the age where we're rebellious" and that running a search engine used by 100 million people a day with 200 employees is "a large responsibility." The number that caught my eye: when Google started in 1998, it indexed 30 million web pages. At the time of this interview, three years later, they indexed 1.3 billion. The page says that if you printed them all out and stacked the paper, it would be about 70 miles high. And it was doubling every year. Every search company they approached turned them down. Yahoo eventually came back and hired Google to power its own search results. The CEO who thought 85% was good enough ran a company that no longer exists. Alphabet, Google's parent company, is worth about $3.6 trillion today. It has about 190,000 employees. That $100,000 check sat in a desk drawer because nobody had incorporated the company. Bechtolsheim's stake from that investment is now worth billions.

Anish Moonka

12,042 просмотров • 3 месяцев назад

✨ I spent the last 48 hours making GPT-4 read the entire Solana validator codebase and write documentation, so doesn't have to. Introducing — an AI-powered chatbot trained on nothing but code that can answer deep technical questions. How it works 👇 But first... A huge shoutout to , Zahid Khawaja, and Sean. Their hard work made prototyping this thing a breeze. Without further ado... Devs like to write code, not documentation. Tribal knowledge is lost when devs move on to other projects, leaving future devs to sort through mountains of code and figure out not just how it works, but why it works that way. This is all about to change. GPT-4's ability to write code is stunning. It seems to understand something fundamental about writing software that previous models just didn't. This comprehension of the principles that drive the design behind a complex system carries over into its ability to document existing codebases in a truly impressive way. With the enlarged context window(s), it's now feasible to feed GPT-4 entire files of code and ask it to write documentation about how the code works. Taking this as a starting point, the process looks something like this: 1. Download repo. 2. Depth-first traversal of repo contents, ignoring things like package-lock and binary files. 3. For each file, feed to GPT-4 and ask it to write documentation in markdown. 4. Save the output in a separate location as [outputRoot]/[inputFilepath][inputFilename].md 5. For each folder, we ask GPT-4 to write a summary of the folder, taking the newly generated documentation for all files in the folder and the summaries from each of its subfolders as context. Write this to the filesystem as markdown. Now we have a filesystem that matches the structure of the input repo, but all files in the tree are markdown documentation of the corresponding code file. From here, we: 1. Load markdown documents into LangChain. 2. Embed all documents via OpenAI embeddings. 3. Store embeddings in Pinecone. When a user sends a query: 1. Embed query. 2. Find k-nearest markdown files. 3. Feed to GPT-4 with a prompt asking to answer the query based on k-nearest markdown documents provided. The craziest part of all this? GPT-4 actually wrote ~30% of the code. The results are pretty good for 2 days of work. There is certainly room for improvement. Some items that are top of mind: 1. TolyGPT will occasionally hallucinate answers. It is especially bad with links to external sources, like GitHub. The base model seems to know a bit about Solana already, and sometimes this creeps in. Fine-tuning the prompt can solve some of this. 2. Context selection is difficult in a codebase this large. For example, sometimes it will pull in details about the Solana SDK when asked about transaction processing. The SDK files can seem relevant depending on the phrasing of the question. It may be worth breaking the documentation into subsystems to limit this. 3. Not all files fit into the 32k token window. As of now, there are 23 (out of ~1,100) files that cannot be documented in their entirety. Some of these files are very important to how Solana works. Final thoughts: 1. GPT-4 is super powerful, and we're going to see a ton of tools that supercharge the entire software development lifecycle. This is not 12 months away. For the people that can afford it, these tools are here now. And they're only getting better. Act accordingly. 2. The price of inference has to come down for this to go mainstream. I spent about $300 prototyping this project, and the final crawl cost about the same. The high cost of GPT-4 will push developers to other, cheaper alternatives with similar performance. This is coming very soon. If you have a large software project and you're interested in something like this for your codebase, fill out this form and we'll be in touch this week. Or just DM me :)

✨ I spent the last 48 hours making GPT-4 read the entire Solana validator codebase and write documentation, so doesn't have to. Introducing — an AI-powered chatbot trained on nothing but code that can answer deep technical questions. How it works 👇 But first... A huge shoutout to , Zahid Khawaja, and Sean. Their hard work made prototyping this thing a breeze. Without further ado... Devs like to write code, not documentation. Tribal knowledge is lost when devs move on to other projects, leaving future devs to sort through mountains of code and figure out not just how it works, but why it works that way. This is all about to change. GPT-4's ability to write code is stunning. It seems to understand something fundamental about writing software that previous models just didn't. This comprehension of the principles that drive the design behind a complex system carries over into its ability to document existing codebases in a truly impressive way. With the enlarged context window(s), it's now feasible to feed GPT-4 entire files of code and ask it to write documentation about how the code works. Taking this as a starting point, the process looks something like this: 1. Download repo. 2. Depth-first traversal of repo contents, ignoring things like package-lock and binary files. 3. For each file, feed to GPT-4 and ask it to write documentation in markdown. 4. Save the output in a separate location as [outputRoot]/[inputFilepath][inputFilename].md 5. For each folder, we ask GPT-4 to write a summary of the folder, taking the newly generated documentation for all files in the folder and the summaries from each of its subfolders as context. Write this to the filesystem as markdown. Now we have a filesystem that matches the structure of the input repo, but all files in the tree are markdown documentation of the corresponding code file. From here, we: 1. Load markdown documents into LangChain. 2. Embed all documents via OpenAI embeddings. 3. Store embeddings in Pinecone. When a user sends a query: 1. Embed query. 2. Find k-nearest markdown files. 3. Feed to GPT-4 with a prompt asking to answer the query based on k-nearest markdown documents provided. The craziest part of all this? GPT-4 actually wrote ~30% of the code. The results are pretty good for 2 days of work. There is certainly room for improvement. Some items that are top of mind: 1. TolyGPT will occasionally hallucinate answers. It is especially bad with links to external sources, like GitHub. The base model seems to know a bit about Solana already, and sometimes this creeps in. Fine-tuning the prompt can solve some of this. 2. Context selection is difficult in a codebase this large. For example, sometimes it will pull in details about the Solana SDK when asked about transaction processing. The SDK files can seem relevant depending on the phrasing of the question. It may be worth breaking the documentation into subsystems to limit this. 3. Not all files fit into the 32k token window. As of now, there are 23 (out of ~1,100) files that cannot be documented in their entirety. Some of these files are very important to how Solana works. Final thoughts: 1. GPT-4 is super powerful, and we're going to see a ton of tools that supercharge the entire software development lifecycle. This is not 12 months away. For the people that can afford it, these tools are here now. And they're only getting better. Act accordingly. 2. The price of inference has to come down for this to go mainstream. I spent about $300 prototyping this project, and the final crawl cost about the same. The high cost of GPT-4 will push developers to other, cheaper alternatives with similar performance. This is coming very soon. If you have a large software project and you're interested in something like this for your codebase, fill out this form and we'll be in touch this week. Or just DM me :)

Sam Hogan 🇺🇸

374,577 просмотров • 3 лет назад

Here's how I'm running automated content engine in 2 files 1 markdown file = my wiki 1 html file = my dashboard that's the whole stack. [ the architecture, in plain words ]: LLM wiki = a single markdown file holding my audience DNA, 15 tracked creators, every viral topic from the last 30 days HTML artifact = a single page that reads that markdown file AND can trigger my agents the artifact and the agent talk to each other directly the wiki is the shared brain [ what I actually see when I open it at 9am ]: > 5 trending topics ranked by my audience-DNA fit > 3 KOL posts worth quoting today > last week's saved tweets (so I can ride waves that are still warm) > buttons: [draft tweet] [draft QT] [schedule] [log idea] 1. I click "draft tweet" on a topic 2. the artifact pings my agent 3. agent reads the wiki, drafts in MY voice, returns it to the artifact 4. I edit, schedule, done 15 minutes from morning coffee to 3 scheduled posts [ how to build the same in one evening ]: > step 1: dump your domain knowledge into ONE markdown file (audience profile, KOL list, content rules, voice guide, anything an agent would need to do YOUR job) > step 2: ask claude to build an html artifact that reads from that file ("here's my wiki, build me a dashboard with these views") > step 3: add buttons for the actions you do daily (draft, schedule, log, score, search — your workflow, not mine) > step 4: wire each button to call your agent via tool calls (so the artifact and the agent talk directly) the moment your artifact reads your wiki AND triggers your agents.. most SaaS tools you currently pay for quietly become unnecessary dashboards I used to pay $50/month for now sit in a single html file I can rebuild in 20 minutes every "I'll build a SaaS for this" idea you had last year is a 200-line file you write in an afternoon if you want to get the same content engine, just reply "CONTENT" and will send you in DMs later we're going from buying software to owning it.

Ronin

49,920 просмотров • 2 месяцев назад

Here is Tuesday's full Karen Read/Aidan Kearney hearing, related to the lawsuit filed by H.A.M., via Canton Community TV (who are wonderful) and Boston 25. To begin, Mark Bederow was approved as pro hac counsel for Aidan Kearney. The Judge, Mark Gildea, then went over the rules for Rule 16 hearings. Judge Gildea moved the case to a fast-track, which would get the case done in two years. TurtleBoy's lawyer noted that both Karen and Aidan intend to file anti-SLAPP motions to dismiss. Aidan's anti-SLAPP will be filed by the end of this week. However, if the plaintiffs amend their pleadings, that timeline could be extended. The anti-SLAPP motion will be 30 pages. The H.A.M. defendants want an entire 30 days to reply to the anti-SLAPP motion, to which Judge said "Why?" The H.A.M. lawyer then asked Judge Gildea, again, for 30 extra days to reply to the anti-SLAPP because the H.A.M. defendants, and the Norfolk D.A., have been served discovery requests by Karen's lawyers. The H.A.M. lawyer then tried to get those documents from the Norfolk D.A. but, because he did not have a protective order, he was unable to get the material. However, the H.A.M. lawyer was caught off guard when Karen and Aidan's lawyers noted to the Judge that an anti-SLAPP motion to dismiss tolls all discovery deadlines. Karen's team has until June 12, 2026 to file that motion. Karen's lawyers, as to the H.A.M. defendants getting their protective order such as to be able to access the documents from the Norfolk D.A. (including potentially devastating evidence from Michael Proctor's personal cellphone about "kill a n-word in Canton day"). We will be back on Thursday June 4, 2026, for a hearing on that protective order issue at 10AM ET (at Plymouth Superior Court). This hearing however, may be cancelled if the parties can agree on a protective order before that date. We will then be back on July 14, 2026, at 2PM ET for a hearing on Aidan and Karen's incoming anti-SLAPP motions to dismiss. The H.A.M. lawyer asked that he be given until July 7th, 2026, to respond to Karen and Aidan's motion, to which the court agreed. Aidan and Karen will be given until July 10, 2026, for a sur-reply. This means discovery will be stayed in the case until, at least, early August of 2026, if not longer. That hearing will also be at at Plymouth Superior Court. This is because, once Karen and Aidan file their anti-SLAPP motions to dismiss, all discovery in the case will stop for the foreseeable future due to procedural, and statutory rules, related to such motions. The H.A.M. lawyer noted that, in light of the anti-SLAPP motion to dismiss, they may amend their complaint. The H.A.M. lawyer noted that, as a result, their response to the coming motions to dismiss under the anti-SLAPP statute will also serve to form the basis for an expansion of their original complaint (permitted until Rule 16). The H.A.M. lawyer obtaining messages from Aidan Kearney's phone, apparently via some kind of third-party network that links back to the Norfolk D.A. and private intelligence firms, was also brought up as, shockingly, a basis for the H.A.M. lawyers attempting to piece Karen's lawyer-client privilege during discovery (thus, potentially, exposing a multi-year operation, dating back to the spring of 2023, to plant private intelligence operatives in Karen and Aidan's orbit for this very purpose). The H.A.M. lawyer also noted they intend to call expert witnesses about, other things, "internet usage." It is unclear if the entire internet, including the "secret" Discord server used by some witnesses during the Karen Read and John O'Keefe trial, will be brought into the record (that was a joke). As of today, John O'Keefe's killer has not been caught. A "Mystery Man", who appeared in edited Canton Police Department Sallyport footage at 5:38PM ET on 1/29/22 (the day of John's death), may be the focus of an upcoming joint state-federal prosecution (should Adam Detich win the Norfolk D.A. primary in September of 2026), although that is only speculation on the part of this reporter. Analysis: When discovery resumes, sometimes in late 2026 or early 2027, this case could indeed become explosive. I have never seen a situation where, three years before litigation, potential private intelligence operatives were used to preemptively establish grounds to pierce Karen's privilege during a civil trial. I will provide more information as I know it.

Here is Tuesday's full Karen Read/Aidan Kearney hearing, related to the lawsuit filed by H.A.M., via Canton Community TV (who are wonderful) and Boston 25. To begin, Mark Bederow was approved as pro hac counsel for Aidan Kearney. The Judge, Mark Gildea, then went over the rules for Rule 16 hearings. Judge Gildea moved the case to a fast-track, which would get the case done in two years. TurtleBoy's lawyer noted that both Karen and Aidan intend to file anti-SLAPP motions to dismiss. Aidan's anti-SLAPP will be filed by the end of this week. However, if the plaintiffs amend their pleadings, that timeline could be extended. The anti-SLAPP motion will be 30 pages. The H.A.M. defendants want an entire 30 days to reply to the anti-SLAPP motion, to which Judge said "Why?" The H.A.M. lawyer then asked Judge Gildea, again, for 30 extra days to reply to the anti-SLAPP because the H.A.M. defendants, and the Norfolk D.A., have been served discovery requests by Karen's lawyers. The H.A.M. lawyer then tried to get those documents from the Norfolk D.A. but, because he did not have a protective order, he was unable to get the material. However, the H.A.M. lawyer was caught off guard when Karen and Aidan's lawyers noted to the Judge that an anti-SLAPP motion to dismiss tolls all discovery deadlines. Karen's team has until June 12, 2026 to file that motion. Karen's lawyers, as to the H.A.M. defendants getting their protective order such as to be able to access the documents from the Norfolk D.A. (including potentially devastating evidence from Michael Proctor's personal cellphone about "kill a n-word in Canton day"). We will be back on Thursday June 4, 2026, for a hearing on that protective order issue at 10AM ET (at Plymouth Superior Court). This hearing however, may be cancelled if the parties can agree on a protective order before that date. We will then be back on July 14, 2026, at 2PM ET for a hearing on Aidan and Karen's incoming anti-SLAPP motions to dismiss. The H.A.M. lawyer asked that he be given until July 7th, 2026, to respond to Karen and Aidan's motion, to which the court agreed. Aidan and Karen will be given until July 10, 2026, for a sur-reply. This means discovery will be stayed in the case until, at least, early August of 2026, if not longer. That hearing will also be at at Plymouth Superior Court. This is because, once Karen and Aidan file their anti-SLAPP motions to dismiss, all discovery in the case will stop for the foreseeable future due to procedural, and statutory rules, related to such motions. The H.A.M. lawyer noted that, in light of the anti-SLAPP motion to dismiss, they may amend their complaint. The H.A.M. lawyer noted that, as a result, their response to the coming motions to dismiss under the anti-SLAPP statute will also serve to form the basis for an expansion of their original complaint (permitted until Rule 16). The H.A.M. lawyer obtaining messages from Aidan Kearney's phone, apparently via some kind of third-party network that links back to the Norfolk D.A. and private intelligence firms, was also brought up as, shockingly, a basis for the H.A.M. lawyers attempting to piece Karen's lawyer-client privilege during discovery (thus, potentially, exposing a multi-year operation, dating back to the spring of 2023, to plant private intelligence operatives in Karen and Aidan's orbit for this very purpose). The H.A.M. lawyer also noted they intend to call expert witnesses about, other things, "internet usage." It is unclear if the entire internet, including the "secret" Discord server used by some witnesses during the Karen Read and John O'Keefe trial, will be brought into the record (that was a joke). As of today, John O'Keefe's killer has not been caught. A "Mystery Man", who appeared in edited Canton Police Department Sallyport footage at 5:38PM ET on 1/29/22 (the day of John's death), may be the focus of an upcoming joint state-federal prosecution (should Adam Detich win the Norfolk D.A. primary in September of 2026), although that is only speculation on the part of this reporter. Analysis: When discovery resumes, sometimes in late 2026 or early 2027, this case could indeed become explosive. I have never seen a situation where, three years before litigation, potential private intelligence operatives were used to preemptively establish grounds to pierce Karen's privilege during a civil trial. I will provide more information as I know it.

Grant Smith Ellis

16,316 просмотров • 1 месяц назад

This Chinese developer launched 6 agents under 1 orchestrator, and they run his UI design agency at $32,000 a month on their own. He built a system of 6 agents on Claude Sonnet 4.6 that single-handedly runs his agency for UI auditing and redesign for SaaS startups and e-commerce. No contractors, no project manager, and no team. Just him, a MacBook, and 1 API key. Traditional design agencies out of Shenzhen keep teams of 8 people on salaries for the same volume, while he keeps only API tokens. 6 agents work through a single orchestrator on Claude Code Router. Usage is about 4 million tokens a day, the average API bill is just $480 a month. All 6 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions. And here is the system prompt he gave the orchestrator before launch: "you are the orchestrator of a one-man UI agency. you delegate read-only research tasks to 5 sub-agents and own all writes. sub-agents: // Hunter (finds SaaS and e-commerce sites with outdated UI) // Auditor (runs each site through Lighthouse, accessibility, and design system checks) // Pitcher (writes cold outreach and redesign proposals with before/after screenshots) // Splitter (breaks accepted projects into typed milestones) // Designer (generates Figma mockups and Tailwind components) // Checker (runs evals on every artifact before it leaves the harness). you never let 2 sub-agents touch 1 file. you stop and request human approval only when an invoice exceeds $5,000 or when the design system eval score drops below 0.88." Meaning the system knows exactly what it is and within what boundaries it operates. It knows it is supposed to find clients on its own. It knows it is supposed to write proposals with screenshots and mockups without intervention. It knows the human only plugs in when the amounts go above $5,000 or when the design system eval does not converge. → The system runs 24 hours a day → Hunter finds about 200 sites with outdated UI a day → Auditor runs each one through Lighthouse and WCAG → Pitcher prepares about 28 personalized proposals with before/after screenshots → Splitter breaks 3 accepted projects per week into milestones → Designer generates mockups and components, Checker runs evals on every artifact And only when the invoice breaks $5,000 or the eval drops below 0.88 does the orchestrator wake the human. Here is what the system outputs in his log during 1 of the sessions: "hunter report, tuesday: 213 sites found, 31 with last redesign before 2020, 14 with Lighthouse score below 65, 6 with active redesign RFP. passing top 6 to auditor." "pitcher: 27 cold outreach sent with before/after screenshots, 5 replies, 3 discovery calls scheduled. passing to splitter." "designer: milestone 2 of Lotus Tea Co redesign complete. Figma frames exported to /Users/dev/agency/clients/lotus/v2. checker running design system evals." "eval flag: proposal for $6,800 exceeds the approved limit of $5,000. sending for manual review." He has no remote server. No separate backend. Just a local file sandbox in /Users/dev/agency, an MCP router, and an API key to Claude. Out of everything I have seen this year, this is the cleanest one-person UI design agency: $480 in, about $32,000 out, and between them 6 prompts and 1 file system.

This Chinese developer launched 6 agents under 1 orchestrator, and they run his UI design agency at $32,000 a month on their own. He built a system of 6 agents on Claude Sonnet 4.6 that single-handedly runs his agency for UI auditing and redesign for SaaS startups and e-commerce. No contractors, no project manager, and no team. Just him, a MacBook, and 1 API key. Traditional design agencies out of Shenzhen keep teams of 8 people on salaries for the same volume, while he keeps only API tokens. 6 agents work through a single orchestrator on Claude Code Router. Usage is about 4 million tokens a day, the average API bill is just $480 a month. All 6 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions. And here is the system prompt he gave the orchestrator before launch: "you are the orchestrator of a one-man UI agency. you delegate read-only research tasks to 5 sub-agents and own all writes. sub-agents: // Hunter (finds SaaS and e-commerce sites with outdated UI) // Auditor (runs each site through Lighthouse, accessibility, and design system checks) // Pitcher (writes cold outreach and redesign proposals with before/after screenshots) // Splitter (breaks accepted projects into typed milestones) // Designer (generates Figma mockups and Tailwind components) // Checker (runs evals on every artifact before it leaves the harness). you never let 2 sub-agents touch 1 file. you stop and request human approval only when an invoice exceeds $5,000 or when the design system eval score drops below 0.88." Meaning the system knows exactly what it is and within what boundaries it operates. It knows it is supposed to find clients on its own. It knows it is supposed to write proposals with screenshots and mockups without intervention. It knows the human only plugs in when the amounts go above $5,000 or when the design system eval does not converge. → The system runs 24 hours a day → Hunter finds about 200 sites with outdated UI a day → Auditor runs each one through Lighthouse and WCAG → Pitcher prepares about 28 personalized proposals with before/after screenshots → Splitter breaks 3 accepted projects per week into milestones → Designer generates mockups and components, Checker runs evals on every artifact And only when the invoice breaks $5,000 or the eval drops below 0.88 does the orchestrator wake the human. Here is what the system outputs in his log during 1 of the sessions: "hunter report, tuesday: 213 sites found, 31 with last redesign before 2020, 14 with Lighthouse score below 65, 6 with active redesign RFP. passing top 6 to auditor." "pitcher: 27 cold outreach sent with before/after screenshots, 5 replies, 3 discovery calls scheduled. passing to splitter." "designer: milestone 2 of Lotus Tea Co redesign complete. Figma frames exported to /Users/dev/agency/clients/lotus/v2. checker running design system evals." "eval flag: proposal for $6,800 exceeds the approved limit of $5,000. sending for manual review." He has no remote server. No separate backend. Just a local file sandbox in /Users/dev/agency, an MCP router, and an API key to Claude. Out of everything I have seen this year, this is the cleanest one-person UI design agency: $480 in, about $32,000 out, and between them 6 prompts and 1 file system.

Blaze

56,062 просмотров • 2 месяцев назад

Here's a copy/paste prompt recipe and vid showing exactly how to ask an LLM for an interactive map with satellite/map layers + a georeferencer that lets you see how old maps correspond with modern geography. Today the computer can’t make good print maps (that's your hill to climb ) but it can, with five bucks and twenty minutes, make good interactive maps. No software/GIS knowledge necessary, you just need a few nouns and an LLM. Scroll to the bottom for the repo/live map if you want those. I'm using Claude Code as an extension in VS Code but you can use the Claude CLI, Cursor, whatever. 1) Let's grab an old cadastral map and see who owned big tracts of a city; I found this an 1854 map of Niagara Falls, NY I found in the Library of Congress: , grabbed the .jp2, saved as a jpg from photoshop. 2) Let's ask Claude Code for a map. You can see exactly what I did in the video but my prompt, sans simple "hey it's busted" debugging, is written out in the following paragraphs. I explain the map-specific nouns in brackets. You can likely dump this whole thing in your LLM window and it'll work; I'd try plan mode + skip permissions. THE PROMPT Make an interactive map with MapLibre GL JS [maplibre is a javascript mapping library, a FOSS version of Mapbox GL JS. This lets us display tiled map data and arbitrary images on the map] Add basemap toggles with Esri satellite, Carto Positron, and OSM [these map layers require no API keys for light usage; Carto Positron is a nice road map layer and OSM is ugly but comprehensive] Add a globe/mercator projection toggle [I think the globe looks better at low zooms] Add a layer panel on the left with visibility checkboxes and delete buttons. Add a search box on the map that flies to results, with deletable pin markers [Makes this easy to get to your area of interest] Include an interactive local georeferencer: drop a JPG, pick ground control points on a zoomable/pannable image viewer, place them on the map, watch it warp with a progress bar centered on the map. [The georeferencer uses math ("affine transform"??) to match points on the old map to points on the new map; generally you click road intersections on the old map, match them on the new map, repeat a dozen times and everything aligns] The georeferenced map overlay defaults to 25% opacity with a slider above the control point list. [I want it easy to see the underlying modern geography] Add Export/import control point buttons [this saves the control points as a JSON so you can save and reimport your work] Add a button to export the warped image as a GeoTIFF with a .prj [In case you want to add the georeferenced image to a real GIS program like QGIS] Look up all relevant docs before starting [Claude sometimes uses outdated stuff] Split everything into separate HTML/CSS/JS files [Claude tends to pile everything in index.html, which is hard to read] Use Optima font, base color #FEFAF6 [I just like this style] Let me test with a local server [it serves it on a simple server so you can nav your host to localhost:8000 and try it out] Log all errors [so you don't have to play telephone with the LLM describing what's busted] 3) Once your LLM finishes, test it out in your browser; if it doesn't work, ask the LLM to check logs. Repeat 'til functional. 4) After this works on your computer, you can show it to everyone by hosting it on GitHub: prompt with "write a README explaining what everything does, add it to a new GitHub repo, deploy using GitHub pages, gimme the live URL" Here's what Claude made for me, try it yourself: • Upload the JPG in the repo, which is linked below • "Add GCP" • Click somewhere recognizable on the old map, like the tip of an island or a road intersection • Click the matching point on the new map • Repeat til you have least 3x points • Hit "georeference" • You'll see the old map atop the new map; if you want a better fit, delete bad points or add a dozen new ones, hit georeference again, repeat Repo: Is this map robust? Human-maintainable? Elegant? Performant? Secure? No, but *your* personal web map need not be. It just needs to work for *your* narrow use case, because it’s *your* map.

Here's a copy/paste prompt recipe and vid showing exactly how to ask an LLM for an interactive map with satellite/map layers + a georeferencer that lets you see how old maps correspond with modern geography. Today the computer can’t make good print maps (that's your hill to climb ) but it can, with five bucks and twenty minutes, make good interactive maps. No software/GIS knowledge necessary, you just need a few nouns and an LLM. Scroll to the bottom for the repo/live map if you want those. I'm using Claude Code as an extension in VS Code but you can use the Claude CLI, Cursor, whatever. 1) Let's grab an old cadastral map and see who owned big tracts of a city; I found this an 1854 map of Niagara Falls, NY I found in the Library of Congress: , grabbed the .jp2, saved as a jpg from photoshop. 2) Let's ask Claude Code for a map. You can see exactly what I did in the video but my prompt, sans simple "hey it's busted" debugging, is written out in the following paragraphs. I explain the map-specific nouns in brackets. You can likely dump this whole thing in your LLM window and it'll work; I'd try plan mode + skip permissions. THE PROMPT Make an interactive map with MapLibre GL JS [maplibre is a javascript mapping library, a FOSS version of Mapbox GL JS. This lets us display tiled map data and arbitrary images on the map] Add basemap toggles with Esri satellite, Carto Positron, and OSM [these map layers require no API keys for light usage; Carto Positron is a nice road map layer and OSM is ugly but comprehensive] Add a globe/mercator projection toggle [I think the globe looks better at low zooms] Add a layer panel on the left with visibility checkboxes and delete buttons. Add a search box on the map that flies to results, with deletable pin markers [Makes this easy to get to your area of interest] Include an interactive local georeferencer: drop a JPG, pick ground control points on a zoomable/pannable image viewer, place them on the map, watch it warp with a progress bar centered on the map. [The georeferencer uses math ("affine transform"??) to match points on the old map to points on the new map; generally you click road intersections on the old map, match them on the new map, repeat a dozen times and everything aligns] The georeferenced map overlay defaults to 25% opacity with a slider above the control point list. [I want it easy to see the underlying modern geography] Add Export/import control point buttons [this saves the control points as a JSON so you can save and reimport your work] Add a button to export the warped image as a GeoTIFF with a .prj [In case you want to add the georeferenced image to a real GIS program like QGIS] Look up all relevant docs before starting [Claude sometimes uses outdated stuff] Split everything into separate HTML/CSS/JS files [Claude tends to pile everything in index.html, which is hard to read] Use Optima font, base color #FEFAF6 [I just like this style] Let me test with a local server [it serves it on a simple server so you can nav your host to localhost:8000 and try it out] Log all errors [so you don't have to play telephone with the LLM describing what's busted] 3) Once your LLM finishes, test it out in your browser; if it doesn't work, ask the LLM to check logs. Repeat 'til functional. 4) After this works on your computer, you can show it to everyone by hosting it on GitHub: prompt with "write a README explaining what everything does, add it to a new GitHub repo, deploy using GitHub pages, gimme the live URL" Here's what Claude made for me, try it yourself: • Upload the JPG in the repo, which is linked below • "Add GCP" • Click somewhere recognizable on the old map, like the tip of an island or a road intersection • Click the matching point on the new map • Repeat til you have least 3x points • Hit "georeference" • You'll see the old map atop the new map; if you want a better fit, delete bad points or add a dozen new ones, hit georeference again, repeat Repo: Is this map robust? Human-maintainable? Elegant? Performant? Secure? No, but your personal web map need not be. It just needs to work for your narrow use case, because it’s your map.

Evan Applegate

15,772 просмотров • 4 месяцев назад

Engineer builds AR ad blocker for real life using Snap Spectacles and Gemini AI | Aamir Khollam, Interesting Engineering A prototype AR app detects ads in your surroundings and blocks them live through Snap Spectacles using Google’s Gemini AI. You can pay for YouTube Premium to avoid watching ads during your sacred food-with-YouTube ritual, or pay for Spotify to not pester you with ads while you try to get a morning workout in, but what can you do about real-life advertisements? A Belgian software developer may have found a workaround. Stijn Spanhove has created an experimental augmented reality app that detects and digitally covers physical ads like billboards and soda cans in the real world. Built for Snap’s fifth-generation AR glasses (Snap Spectacles), the prototype uses Google’s Gemini AI to identify branded content and instantly mask it. Instead of the original imagery, the app places a bright red square over the detected ad. These red blocks also name the hidden brand, like “Bol. billboard,” turning ad removal into a kind of real-time brand callout. “It’s exciting to imagine a future where you control the physical content you see,” Spanhove posted on X (formerly Twitter). In follow-up replies, he hinted at additional features, including options to replace the red square with personal photos or text from a notes app. Check it out below – Combines Snap and Google tools The app relies on Snap’s Depth Cache API to register objects in 3D space and maintain spatial consistency as the user moves. Gemini, Google’s generative AI model, identifies the ads themselves, whether on large posters, newspaper pages, or food packaging. This allows the blocker to function beyond obvious signage. In demo clips shared by Spanhove, it successfully covers ads on cereal boxes, magazines, and public signage, though not without a delay of a second or two. The red overlays appear to float stably, following head movements and perspective shifts with accuracy. Still, it’s early days. Spanhove describes the software as “experimental,” and the user experience reflects that. Because Snap Spectacles use transparent displays, the overlays can’t fully block light, so the original ad sometimes faintly shows through. Also, the Spectacles’ narrow 46-degree field of view limits coverage to only what’s directly ahead. Design stirs debate The app has sparked strong reactions online. Many praised the concept of user-controlled visual space, while others criticized the bold red boxes as more jarring than the ads themselves. One suggestion, from user Hexographer ⬣Backup account⬣, proposed replacing the red blocks with more visually pleasing alternatives, such as “images of local foliage or animal life.” They also suggested that users could set a custom folder of replacement visuals, including personal or family photos. Others asked for cross-platform support, but the app currently only works with Snap Spectacles. Devices like the Apple Vision Pro or Meta Quest will need separate development efforts. Despite its limitations, the project arrives at a moment when major tech firms like Meta and Microsoft have scaled back their AR ambitions. Snap, meanwhile, continues renting its Spectacles to developers at $99 per month, making experiments like Spanhove’s possible. Read more:

Owen Gregorian

45,774 просмотров • 1 год назад

Wait, what? Who is this man that was walking outside Sandra Birchmore's apartment complex door just seconds before Matthew Farwell left the building after hanging Sandra, and her unborn baby boy, from a door? Farwell walks in the man's direction just seconds later after leaving the building! CC: U.S. Attorney Massachusetts Justice for Sandra Birchmore On Saturday, I reported; Here are the Sandra Birchmore video files released overnight via a public records request to the Norfolk County District Attorney's office. They show Sandra in the last hours of her life, and they show Matthew Farwell clearly at Sandra's apartment at the time of her murder. Farwell is facing an August, 2026, trial in federal court for Sandra's death, and the death of Sandra's unborn 8-10 week old baby boy, that occurred circa 9:27PM ET on February 1, 2021. Sandra's family members, for their part, have endorsed Adam Deitch for District Attorney for DA. Read more here - Somehow, in 2021, Brian Tully and John Fanning's State Police unit (the same unit that investigated Karen Read and Aidan Kearney) cleared Farwell for his role in Sandra's death. Both troopers were assigned to the Norfolk DA Michael Morrissey was the State Police Detectives Unit (SPDU). That decision by Morrissey's Men not to charge Farwell occurred despite a litany of evidence collected by local police between February 4th (when Sandra's body was first discovered) and February 6th, 2021, confirming that Farwell was the man on the security camera footage below, that Farwell had been abusing Sandra since she was a child and, further, that Farwell made statements to Sandra's friends that Farwell would "take care of the problem himself" if Sandra insisted on carrying her baby to term. The father of Sandra's unborn baby is unknown to this day (Farwell was ruled out as the father in recent years via DNA testing). Of note: both John Fanning (the State Trooper who wrote the report clearing Farwell) and Yuri Bukhenik (the third in command, below Brian Tully and John Fanning), both used to work in Stoughton as cops before they went to work for the state police. Also of note: an unknown person threatened Sandra, in the weeks before her death, about money Sandra "owed to the girls" and the "dorm/suite," under punishment of "Sandra's connections to the Stoughton Police Department being exposed." (See attached images 2 and 3.) Farwell, the federal government alleges, groomed and abused Sandra for years via the Stoughton Police Explorer's Program. Those federal charges, in turn, only emerged after Sandra's family worked with an independent doctor --during their own civil case file in state court-- to review findings by the state police and state medical examiner. That doctor is the husband of Justice Served TV host Linda Kenney Baden. Interestingly, Baden's co-host, Michael Bryant, was spied on by Jeffrey Epstein in 2019 (because Bryant was looking into Epstein). Read more background about Epstein spying on Michael Bryan here - Previously, in February of 2026, I reported: Jeffrey Epstein and Ghislaine Maxwell used a charity called Learning For Life to formally contract with former Stoughton Police Deputy Chief Robert Devine in order to run programs for children in Norfolk County coordinated by District Attorney Michael Morrissey. (See attached image 1.) Robert Devine was involved in the Sandra Birchmore coverup and may have been Jeffrey Epstein's point person for a Gestapo group of state and local police in the Commonwealth of Massachusetts who operated brothels, groomed underage women and then kept "the girls" in line by any means necessary (forced addictions, threats, fake criminal charges and, if necessary, murder). Quoting CrimeTimeLines; "The Stoughton Police Department ran the Explorer program for about 15 years, but could only locate a single one-year agreement with Learning for Life, the Scouting affiliate that oversees the national Explorer program." "Robert C. Devine has led the Stoughton Police Explorers Program since 2003, a youth initiative under the department." Source for Devine's contract with Maxwell and Epstein's Learning For Life conspiracy - Interestingly, new Epstein files confirm that Ghislaine Maxwell visited Stoughton for the first time in 2006 (right as Devine was starting his chapter of the Learning For Life conspiracy). Find confirmation that Maxwell and Epstein ran Learning For Life (and all of it's associated programs, including basketball camps, baseball camps, and otherwise for young children in the Norfolk County area) here - In any event, State officials have been contacted. I am working to immediately end all of these programs. I will have more information shortly. Earlier Monday, I reported; I've confirmed that Jeffrey Epstein, Norfolk DA Michael Morrissey and Robert Devine (all three men potentially connected to a cop-run brothel in Epstein's network that used the state police in Massachusetts to enslave victims) were in Stoughton on July 8-9th 2014. Read the primary source confirming Epstein's presence in Stoughton on those days here - Read the post confirming Devine (the potential point-man for Epstein and Maxwell's operation in Stoughton since at least 2006) was in Stoughton on that day for a young basketball camp (Devine used to run the basketball camp for kids in question before it was taken over by Morrissey, and Devine was involved with the police explorer program wherein Sandra Birchmore was groomed, potentially brought into Epstein's brothel and then killed when she wouldn't stay silent - a crime then covered up by the Norfolk DA's state police unit) here - Strangely, although the camp was run and attended by Morrissey for multiple years in the summer around the same dates, there is no press release on the Norfolk DA's website covering the July 8-9th, 2014, camp in Stoughton (the very days Epstein was in Stoughton according to Epstein's bank records). Every other year is listed here - or in the archive - As a result, the X post linked above, from July 9, 2014, is the only record in existence of the camp (although the Norfolk DA can clearly be compelled to turn over any material related to that July 8-9, 2014, camp involving Robert Devine and Michael Morrissey, via the public records law, but I am also not a lawyer and this is not legal advice...I am a towel). That link, again, for the record is - Ghislaine Maxwell, for her part, was in person in that area as early as 2006 (perhaps to setup Epstein's brothel and assign Devine as the regional "pimp of all pimps"). Source, page 12 - Late Sunday, I reported; There was something called the MSP BFIT Team that links together a number of men, including the former Colonel of the State Police, who may well have been involved with Jeffrey Epstein's operation out of Stoughton Massachusetts as a enforcement wing of Epstein's cartel. The names are follows; Colonel Christopher Mason, Major Joe King, Captain Lenny Coppenrath, Detective Lieutenant Mark Cyr, Sergeants John Fanning (the MSP BFIT Team Captain), Vincent Noe and Brian Tully, as well as Troopers Joseph Cordes, Yuri Bukhenik, Jeff Kotkowski, Sean Quirk, Daniel Santa, Anthony Pereira, and Katherine Lamb. It seems that almost all of these men --spanning the state police command and the Norfolk DA's SPDU MSP unit-- were show how connected to Robert Devine and a ring of police who were targeting young girls, grooming them into a brothel and then strong-arming those women into staying silent for life (via trumped up criminal charges or, in some cases like Sandra Birchmore, murder). Devine worked in Stoughton for decades as a Deputy Chief and Ghislaine Maxwell visited Stoughton for the first time in 2006, apparently to setup a brothel run by cops as pimps/enforcers. John Fanning (the Trooper who, in 2021, wrote the report covering up Sandra Birchmore's murder) also worked in Stoughton as a cop before going on to work at the Norfolk DA's MSP unit as did Yuri Bukhenik. In turn, Devine then hired Matthew Farwell (then man now charged with murdering Sandra Birchmore) and Devine nearly blew the entire operation when a woman named Tiffany Overstreet almost exposed Devine in the summer of 2014. Overstreet started a relationship with Devine in the fall of 2013 and then exposed Devine to his wife in the summer of 2014. Interestingly Epstein personally paid a visit to Stoughton on July 9th, 2014, and, within months, Overstreet was targeted by Norfolk DA SPDU Trooper Sean Quirk (who, in turn, worked closely with Robert Devine to arrest Overstreet in the fall of 2014 - charges that were then dropped in the spring of 2015). Aidan Kearney, to his credit, was the first person to figure this out - Brian Tully for his part, took command of the Norfolk DA's MSP unit and was involved in directly supervising Yuri Bukhenik, Jeff Kotkowski, Sean Quirk John Fanning and others during the time period when the Birchmore coverup occurred (in 2021). Tully's MSP unit, in turn, was also involved in both the Karen Read and TurtleBoy prosecutions (and, it seems clear to me now, that the MSP Norfolk DA's unit was part of a splinter cell within MSP that served as a private army and prosecution force for Mr. Epstein...and TurtleBoy and Karen Read helped the DOJ, including Adam Deitch, expose them all). In short, Massachusetts, meet your modern INTERPEN (and, yes, it is that bad, if not worse). Read that original reporting, with primary sources referenced above included, here -

Wait, what? Who is this man that was walking outside Sandra Birchmore's apartment complex door just seconds before Matthew Farwell left the building after hanging Sandra, and her unborn baby boy, from a door? Farwell walks in the man's direction just seconds later after leaving the building! CC: U.S. Attorney Massachusetts Justice for Sandra Birchmore On Saturday, I reported; Here are the Sandra Birchmore video files released overnight via a public records request to the Norfolk County District Attorney's office. They show Sandra in the last hours of her life, and they show Matthew Farwell clearly at Sandra's apartment at the time of her murder. Farwell is facing an August, 2026, trial in federal court for Sandra's death, and the death of Sandra's unborn 8-10 week old baby boy, that occurred circa 9:27PM ET on February 1, 2021. Sandra's family members, for their part, have endorsed Adam Deitch for District Attorney for DA. Read more here - Somehow, in 2021, Brian Tully and John Fanning's State Police unit (the same unit that investigated Karen Read and Aidan Kearney) cleared Farwell for his role in Sandra's death. Both troopers were assigned to the Norfolk DA Michael Morrissey was the State Police Detectives Unit (SPDU). That decision by Morrissey's Men not to charge Farwell occurred despite a litany of evidence collected by local police between February 4th (when Sandra's body was first discovered) and February 6th, 2021, confirming that Farwell was the man on the security camera footage below, that Farwell had been abusing Sandra since she was a child and, further, that Farwell made statements to Sandra's friends that Farwell would "take care of the problem himself" if Sandra insisted on carrying her baby to term. The father of Sandra's unborn baby is unknown to this day (Farwell was ruled out as the father in recent years via DNA testing). Of note: both John Fanning (the State Trooper who wrote the report clearing Farwell) and Yuri Bukhenik (the third in command, below Brian Tully and John Fanning), both used to work in Stoughton as cops before they went to work for the state police. Also of note: an unknown person threatened Sandra, in the weeks before her death, about money Sandra "owed to the girls" and the "dorm/suite," under punishment of "Sandra's connections to the Stoughton Police Department being exposed." (See attached images 2 and 3.) Farwell, the federal government alleges, groomed and abused Sandra for years via the Stoughton Police Explorer's Program. Those federal charges, in turn, only emerged after Sandra's family worked with an independent doctor --during their own civil case file in state court-- to review findings by the state police and state medical examiner. That doctor is the husband of Justice Served TV host Linda Kenney Baden. Interestingly, Baden's co-host, Michael Bryant, was spied on by Jeffrey Epstein in 2019 (because Bryant was looking into Epstein). Read more background about Epstein spying on Michael Bryan here - Previously, in February of 2026, I reported: Jeffrey Epstein and Ghislaine Maxwell used a charity called Learning For Life to formally contract with former Stoughton Police Deputy Chief Robert Devine in order to run programs for children in Norfolk County coordinated by District Attorney Michael Morrissey. (See attached image 1.) Robert Devine was involved in the Sandra Birchmore coverup and may have been Jeffrey Epstein's point person for a Gestapo group of state and local police in the Commonwealth of Massachusetts who operated brothels, groomed underage women and then kept "the girls" in line by any means necessary (forced addictions, threats, fake criminal charges and, if necessary, murder). Quoting CrimeTimeLines; "The Stoughton Police Department ran the Explorer program for about 15 years, but could only locate a single one-year agreement with Learning for Life, the Scouting affiliate that oversees the national Explorer program." "Robert C. Devine has led the Stoughton Police Explorers Program since 2003, a youth initiative under the department." Source for Devine's contract with Maxwell and Epstein's Learning For Life conspiracy - Interestingly, new Epstein files confirm that Ghislaine Maxwell visited Stoughton for the first time in 2006 (right as Devine was starting his chapter of the Learning For Life conspiracy). Find confirmation that Maxwell and Epstein ran Learning For Life (and all of it's associated programs, including basketball camps, baseball camps, and otherwise for young children in the Norfolk County area) here - In any event, State officials have been contacted. I am working to immediately end all of these programs. I will have more information shortly. Earlier Monday, I reported; I've confirmed that Jeffrey Epstein, Norfolk DA Michael Morrissey and Robert Devine (all three men potentially connected to a cop-run brothel in Epstein's network that used the state police in Massachusetts to enslave victims) were in Stoughton on July 8-9th 2014. Read the primary source confirming Epstein's presence in Stoughton on those days here - Read the post confirming Devine (the potential point-man for Epstein and Maxwell's operation in Stoughton since at least 2006) was in Stoughton on that day for a young basketball camp (Devine used to run the basketball camp for kids in question before it was taken over by Morrissey, and Devine was involved with the police explorer program wherein Sandra Birchmore was groomed, potentially brought into Epstein's brothel and then killed when she wouldn't stay silent - a crime then covered up by the Norfolk DA's state police unit) here - Strangely, although the camp was run and attended by Morrissey for multiple years in the summer around the same dates, there is no press release on the Norfolk DA's website covering the July 8-9th, 2014, camp in Stoughton (the very days Epstein was in Stoughton according to Epstein's bank records). Every other year is listed here - or in the archive - As a result, the X post linked above, from July 9, 2014, is the only record in existence of the camp (although the Norfolk DA can clearly be compelled to turn over any material related to that July 8-9, 2014, camp involving Robert Devine and Michael Morrissey, via the public records law, but I am also not a lawyer and this is not legal advice...I am a towel). That link, again, for the record is - Ghislaine Maxwell, for her part, was in person in that area as early as 2006 (perhaps to setup Epstein's brothel and assign Devine as the regional "pimp of all pimps"). Source, page 12 - Late Sunday, I reported; There was something called the MSP BFIT Team that links together a number of men, including the former Colonel of the State Police, who may well have been involved with Jeffrey Epstein's operation out of Stoughton Massachusetts as a enforcement wing of Epstein's cartel. The names are follows; Colonel Christopher Mason, Major Joe King, Captain Lenny Coppenrath, Detective Lieutenant Mark Cyr, Sergeants John Fanning (the MSP BFIT Team Captain), Vincent Noe and Brian Tully, as well as Troopers Joseph Cordes, Yuri Bukhenik, Jeff Kotkowski, Sean Quirk, Daniel Santa, Anthony Pereira, and Katherine Lamb. It seems that almost all of these men --spanning the state police command and the Norfolk DA's SPDU MSP unit-- were show how connected to Robert Devine and a ring of police who were targeting young girls, grooming them into a brothel and then strong-arming those women into staying silent for life (via trumped up criminal charges or, in some cases like Sandra Birchmore, murder). Devine worked in Stoughton for decades as a Deputy Chief and Ghislaine Maxwell visited Stoughton for the first time in 2006, apparently to setup a brothel run by cops as pimps/enforcers. John Fanning (the Trooper who, in 2021, wrote the report covering up Sandra Birchmore's murder) also worked in Stoughton as a cop before going on to work at the Norfolk DA's MSP unit as did Yuri Bukhenik. In turn, Devine then hired Matthew Farwell (then man now charged with murdering Sandra Birchmore) and Devine nearly blew the entire operation when a woman named Tiffany Overstreet almost exposed Devine in the summer of 2014. Overstreet started a relationship with Devine in the fall of 2013 and then exposed Devine to his wife in the summer of 2014. Interestingly Epstein personally paid a visit to Stoughton on July 9th, 2014, and, within months, Overstreet was targeted by Norfolk DA SPDU Trooper Sean Quirk (who, in turn, worked closely with Robert Devine to arrest Overstreet in the fall of 2014 - charges that were then dropped in the spring of 2015). Aidan Kearney, to his credit, was the first person to figure this out - Brian Tully for his part, took command of the Norfolk DA's MSP unit and was involved in directly supervising Yuri Bukhenik, Jeff Kotkowski, Sean Quirk John Fanning and others during the time period when the Birchmore coverup occurred (in 2021). Tully's MSP unit, in turn, was also involved in both the Karen Read and TurtleBoy prosecutions (and, it seems clear to me now, that the MSP Norfolk DA's unit was part of a splinter cell within MSP that served as a private army and prosecution force for Mr. Epstein...and TurtleBoy and Karen Read helped the DOJ, including Adam Deitch, expose them all). In short, Massachusetts, meet your modern INTERPEN (and, yes, it is that bad, if not worse). Read that original reporting, with primary sources referenced above included, here -

Grant Smith Ellis

69,714 просмотров • 26 дней назад

Anthropic released Claude Design TODAY and it's now accessible at I spent the last hour giving it a first look, and shared my thoughts and results in the video below. This is a BIG drop. This is a new design surface from Anthropic, and it changes what "AI design" means. Short version: Claude can now design. Not "describe a design." Not "generate an image of a design." Actual production work — prototypes, wireframes, high-fidelity mocks, slide decks, landing pages — editable, on-brand, and ready to hand off. Here's what stood out on first look: → Real design surfaces Prototypes, wireframes, hi-fi, and slide decks — each with templates and proper structure, not just pretty screenshots. → Comment-based edits Leave a comment on any element and Claude revises it. This is the Figma-style review loop, with the designer replaced by a model that works at 3am. → Brand design systems You can feed it your system — colors, type, components — and it actually respects it. On-brand output, not generic AI slop. → Export anywhere PDF, PowerPoint, Canva, standalone HTML. Plus a built-in handoff straight to Claude Code for engineers to implement. → Import from real tools Figma, GitHub, and captured web elements come in as inputs. Your existing work is the starting line, not the discard pile. → Collaboration Share links for view / comment / edit — the exact tier system teams already expect. What I tested on Opus 4.7: • A 5-slide deck generated from a single screenshot. Claude asked clarifying questions BEFORE generating and shipped speaker notes by default. • A landing page build. Solid first pass, real components, real layout logic. • Multiple chats running concurrently. You can parallelize design work across threads like a small team. Why this matters: PMs, founders, marketers, and non-engineers can now create designs that engineers can actually ship with production-ready output and a claude code handoff built in. The gap between "I have an idea" and "here's a working prototype with my brand applied" just collapsed to minutes. Full walkthrough, live demos, exports, and honest takes on where it breaks below. P.S. • This is an Anthropic Labs product — NOT GA yet. • Claude Design is currently webapp only (no API), and does not yet support the Analytics API, Compliance API, or cost/usage reporting. • Availability: – Default ON for Pro / Max / Team – Default OFF for Enterprise Enterprise admins can toggle it on via RBAC in console (comes with a ~$20/user initial credit).

JJ Englert

32,445 просмотров • 3 месяцев назад

WHO KILLED CHARLIE KIRK? It has taken me some time to speak about our friendship with Charlie Kirk, but Yvonne Ridley is an old friend whom I have known since 1995. She is also one of the finest investigative journalists Britain has ever produced. Over the years, she and I have occupied different parts of the political spectrum, but she has always been honest and respectful, and we have always shared one fundamental agreement: we both completely oppose unnecessary war, and we detest those who profit from it. When I purchased our newspaper group in London, I was honoured that Yvonne—already a highly successful mainstream journalist with The Sunday Times and The Express and other prestigious broadsheets—asked to write a column for our titles. One day in late 2001, she rather surprised me by calling to say that she was going into Afghanistan to expose the refugee crisis that had been created on the border of Afghanistan and Pakistan by Western bellicose intentions during the buildup to military action post 9/11. A few days later, Yvonne was arrested by the Taliban and faced public execution as a presumed spy. It is a longer story, but we campaigned tirelessly to secure her release. Far from being a spy Yvonne was there to expose the consequences of the proposed military engagement. Although he may not recall it, Piers Morgan was very sympathetic to the plight of a captured British journalist and he helped our campaign tremendously. Piers was editor of the Daily Mirror at that time ( on of Britain's most successful tabloids, and I was the humble inexperienced new owner of a small local newspaper group but he took my call, and Yvone and her fate which hung in the balance and with the good will of a beset Taliban became front-page news across the United Kingdom. I remember that we lit a Fire Beacon 🔥at Camelot Castle to alert the media to the fate of this brave freedom fighting peace loving British journalist. What began in a few local papers quickly caught the national imagination. On the back of that, a timely letter that Irina (Irina Mappin) and I wrote to Nursultan Nazarbayev, who was travelling in Turkey at the time, resulted in a presidential intervention via Kabul. The Kazakh President Kazakhstan 🇰🇿 Kazakh Embassy 🇰🇿 to UK 🇬🇧 secured her release just one day before Allied forces struck the city with the full force of western military might. So life is interesting as a journalist and as a Newspaper Owner. A few weeks ago, 25 years on, Yvonne Ridley (Yvonne Ridley 4 Glasgow) saw the letter Irina and I had written in defence of Candace Owens Candace Owens and contacted me to suggest that I speak with her about Charlie’s execution. I had given only one brief interview to the exceptional Celia Walden Celia Walden on the subject. That had been a print interview, and I did not know how well I would hold up on video or a filmed podcast. I do not mind sharing with you that Charlie’s execution has been an extremely difficult experience for our family. One of the toughest things in my life so far. Being someone who does not readily share their raw emotion, and in all honesty prefers not to, I have declined multiple video interview requests from respected journalists around the world. But now people are asking sincere questions, and frankly, I am asking questions too. Much does not make sense to me based on what I know to be true. The fact that Yvonne has taken an interest in this subject and in others investigation is extremely important for all those who care about the truth. Not least because Yvonne has been, and remains, one of the most formidable and persistant investigative journalists Great Britain has ever produced. I suspect that this will not be the last that you hear from her on this subject. I hope you find the full interview interesting you will find it in the link below in the thread. Charlie was a unique human being and he was our friend. My father taught me very early on in life. That we never abandon our friends. Not in life, And certainly not in the event of their death. Irina and I woudl like to convey our thanks to all those people across the world that are working for truth, for sanity and for peace. For that is what we did with Charlie. All our love John and Irina. Skyhorse Publishing

WHO KILLED CHARLIE KIRK? It has taken me some time to speak about our friendship with Charlie Kirk, but Yvonne Ridley is an old friend whom I have known since 1995. She is also one of the finest investigative journalists Britain has ever produced. Over the years, she and I have occupied different parts of the political spectrum, but she has always been honest and respectful, and we have always shared one fundamental agreement: we both completely oppose unnecessary war, and we detest those who profit from it. When I purchased our newspaper group in London, I was honoured that Yvonne—already a highly successful mainstream journalist with The Sunday Times and The Express and other prestigious broadsheets—asked to write a column for our titles. One day in late 2001, she rather surprised me by calling to say that she was going into Afghanistan to expose the refugee crisis that had been created on the border of Afghanistan and Pakistan by Western bellicose intentions during the buildup to military action post 9/11. A few days later, Yvonne was arrested by the Taliban and faced public execution as a presumed spy. It is a longer story, but we campaigned tirelessly to secure her release. Far from being a spy Yvonne was there to expose the consequences of the proposed military engagement. Although he may not recall it, Piers Morgan was very sympathetic to the plight of a captured British journalist and he helped our campaign tremendously. Piers was editor of the Daily Mirror at that time ( on of Britain's most successful tabloids, and I was the humble inexperienced new owner of a small local newspaper group but he took my call, and Yvone and her fate which hung in the balance and with the good will of a beset Taliban became front-page news across the United Kingdom. I remember that we lit a Fire Beacon 🔥at Camelot Castle to alert the media to the fate of this brave freedom fighting peace loving British journalist. What began in a few local papers quickly caught the national imagination. On the back of that, a timely letter that Irina (Irina Mappin) and I wrote to Nursultan Nazarbayev, who was travelling in Turkey at the time, resulted in a presidential intervention via Kabul. The Kazakh President Kazakhstan 🇰🇿 Kazakh Embassy 🇰🇿 to UK 🇬🇧 secured her release just one day before Allied forces struck the city with the full force of western military might. So life is interesting as a journalist and as a Newspaper Owner. A few weeks ago, 25 years on, Yvonne Ridley (Yvonne Ridley 4 Glasgow) saw the letter Irina and I had written in defence of Candace Owens Candace Owens and contacted me to suggest that I speak with her about Charlie’s execution. I had given only one brief interview to the exceptional Celia Walden Celia Walden on the subject. That had been a print interview, and I did not know how well I would hold up on video or a filmed podcast. I do not mind sharing with you that Charlie’s execution has been an extremely difficult experience for our family. One of the toughest things in my life so far. Being someone who does not readily share their raw emotion, and in all honesty prefers not to, I have declined multiple video interview requests from respected journalists around the world. But now people are asking sincere questions, and frankly, I am asking questions too. Much does not make sense to me based on what I know to be true. The fact that Yvonne has taken an interest in this subject and in others investigation is extremely important for all those who care about the truth. Not least because Yvonne has been, and remains, one of the most formidable and persistant investigative journalists Great Britain has ever produced. I suspect that this will not be the last that you hear from her on this subject. I hope you find the full interview interesting you will find it in the link below in the thread. Charlie was a unique human being and he was our friend. My father taught me very early on in life. That we never abandon our friends. Not in life, And certainly not in the event of their death. Irina and I woudl like to convey our thanks to all those people across the world that are working for truth, for sanity and for peace. For that is what we did with Charlie. All our love John and Irina. Skyhorse Publishing

John Mappin

83,393 просмотров • 5 месяцев назад

A National Inquiry That Refuses to Name the Guilty Will Fail In 2013, the Home Affairs Select Committee recorded that senior officials in Rochdale and Rotherham had failed in their duty of care to children subjected to organised sexual abuse. The Committee identified responsibility up the chain of command. It named the council Chief Executive, the Director of Children’s Services, the Local Safeguarding Children Board, and individual practitioners. It recorded that senior figures claimed not to know about the abuse during years when it was documented by frontline staff. That claim of ignorance was rejected. The Committee stated it was no excuse. It stated that those in senior positions were responsible for the consequences of their inaction. Despite the conclusions of one of the most powerful government committees; - No criminal investigation into senior officials followed. - No police force opened misconduct inquiries into those named. - No minister referred the findings for prosecution. The Committee also recorded that Rotherham had secured 'no prosecutions relating to organised child sexual exploitation since 2010.' That finding was published in 2013. The first significant prosecutions in Rotherham relating to organised child sexual exploitation took place years later, following further public exposure and additional reports. Those prosecutions were brought ONLY against a handful of perpetrators. They did not include senior council officers, police commanders, or safeguarding leads identified in the earlier parliamentary findings. No individual named by Parliament in 2013 was charged. Political decisions taken after 2013 determined how these findings were handled. The Home Affairs Select Committee report was the closest the state came to pursuing those responsible for failing children and for suppressing the truth. It identified senior officials, rejected claims of ignorance, and stated that responsibility rested at the top. What followed was a retreat. The Jay Report documented prolonged abuse and institutional neglect in Rotherham. It confirmed the scale of harm already known to Parliament. It did not pursue criminal liability for senior officials. No referrals were made. Responsibility was redirected into local reform. Telford later confirmed industrial-scale exploitation and repeated police failure. Again, the findings did not lead to criminal proceedings against senior decision-makers. No prosecutions followed. In Greater Manchester, reviews were commissioned with terms that limited examination to organisational learning. Individual criminal responsibility was excluded from scope. That exclusion was accepted. No request was made to widen it. Across each case, the same decision was repeated; - record harm - exclude liability - move on. Language changed. Structures were altered. Senior figures exited quietly. Criminal accountability never followed. Only after years of pressure from victims, journalists, and campaigners has a National Inquiry been forced. That inquiry now sits at the same decision point reached in 2013. Whether to follow responsibility where Parliament already traced it or to retreat again. A National Inquiry has now been confirmed. Its Terms of Reference are being consulted on. Under the Inquiries Act 2005, an inquiry may act only within its Terms of Reference. If individual responsibility and criminal referral are not explicitly required, they can be lawfully avoided. Previous inquiries operated within those limits. Harm was described. Failures were recorded. Individuals were not named. Prosecution did not follow. This Inquiry will do the same unless its remit is written differently. What You Can Do Now Contact your MP and ask one question only. Will they write to Baroness Anne Longfield demanding that the Terms of Reference explicitly require the Inquiry to name individuals, examine political decision-making, make findings where conduct may meet criminal thresholds, and refer cases for prosecution. Responses will be published. Silence will be recorded. The consultation closes soon. After that, the outcome is already set. Use the draft below. Do not deviate from it. Subject: Will you write to Anne Longfield on Inquiry powers and accountability? Dear [MP NAME], In 2013, Parliament’s Home Affairs Select Committee recorded that senior officials had failed in their duty of care to children subjected to organised sexual abuse. Those officials were identified. No prosecutions followed. Under section 5(5) of the Inquiries Act 2005, a statutory inquiry may act only within its Terms of Reference. Unless individual accountability and referral are explicitly required, an inquiry can avoid naming individuals or recommending criminal investigation. Will you write to Baroness Anne Longfield requesting that the Terms of Reference explicitly require the Inquiry to: - identify by name individuals whose acts or omissions may meet criminal thresholds, including misconduct in public office; and - refer such cases to the police and the Crown Prosecution Service. Please confirm, yes or no, whether you will do so. Yours sincerely, [NAME] _________ I need your help. My work is free. No paywalls. No gatekeeping. No exclusions. Because the truth shouldn’t belong only to those who can afford it. I’m Raja Miah MBE. For seven years, I led a campaign that exposed how senior Labour politicians helped protect Pakistani rape gangs and helped force a national inquiry. You won’t see me on the BBC. You won’t read my work in the legacy press. That’s not an accident. I take this to a place from where there is no coming back. I document everything in my newsletter. It’s 100% free to read. If this work matters to you, if you believe it must continue, I need your backing. 🔴 Supporting me costs as little as 75p a week (£30 a year): 👉 If you can’t do monthly, a one-off contribution genuinely helps keep this alive: 👉 👉 We’re up against a machine, politicians, police, officials, and media, working together to shrink, sanitise, and bury the truth. This work survives because of you. If you’ve ever shared my posts, learned something, or felt less alone reading them, stand with me. Raja 🙏

A National Inquiry That Refuses to Name the Guilty Will Fail In 2013, the Home Affairs Select Committee recorded that senior officials in Rochdale and Rotherham had failed in their duty of care to children subjected to organised sexual abuse. The Committee identified responsibility up the chain of command. It named the council Chief Executive, the Director of Children’s Services, the Local Safeguarding Children Board, and individual practitioners. It recorded that senior figures claimed not to know about the abuse during years when it was documented by frontline staff. That claim of ignorance was rejected. The Committee stated it was no excuse. It stated that those in senior positions were responsible for the consequences of their inaction. Despite the conclusions of one of the most powerful government committees; - No criminal investigation into senior officials followed. - No police force opened misconduct inquiries into those named. - No minister referred the findings for prosecution. The Committee also recorded that Rotherham had secured 'no prosecutions relating to organised child sexual exploitation since 2010.' That finding was published in 2013. The first significant prosecutions in Rotherham relating to organised child sexual exploitation took place years later, following further public exposure and additional reports. Those prosecutions were brought ONLY against a handful of perpetrators. They did not include senior council officers, police commanders, or safeguarding leads identified in the earlier parliamentary findings. No individual named by Parliament in 2013 was charged. Political decisions taken after 2013 determined how these findings were handled. The Home Affairs Select Committee report was the closest the state came to pursuing those responsible for failing children and for suppressing the truth. It identified senior officials, rejected claims of ignorance, and stated that responsibility rested at the top. What followed was a retreat. The Jay Report documented prolonged abuse and institutional neglect in Rotherham. It confirmed the scale of harm already known to Parliament. It did not pursue criminal liability for senior officials. No referrals were made. Responsibility was redirected into local reform. Telford later confirmed industrial-scale exploitation and repeated police failure. Again, the findings did not lead to criminal proceedings against senior decision-makers. No prosecutions followed. In Greater Manchester, reviews were commissioned with terms that limited examination to organisational learning. Individual criminal responsibility was excluded from scope. That exclusion was accepted. No request was made to widen it. Across each case, the same decision was repeated; - record harm - exclude liability - move on. Language changed. Structures were altered. Senior figures exited quietly. Criminal accountability never followed. Only after years of pressure from victims, journalists, and campaigners has a National Inquiry been forced. That inquiry now sits at the same decision point reached in 2013. Whether to follow responsibility where Parliament already traced it or to retreat again. A National Inquiry has now been confirmed. Its Terms of Reference are being consulted on. Under the Inquiries Act 2005, an inquiry may act only within its Terms of Reference. If individual responsibility and criminal referral are not explicitly required, they can be lawfully avoided. Previous inquiries operated within those limits. Harm was described. Failures were recorded. Individuals were not named. Prosecution did not follow. This Inquiry will do the same unless its remit is written differently. What You Can Do Now Contact your MP and ask one question only. Will they write to Baroness Anne Longfield demanding that the Terms of Reference explicitly require the Inquiry to name individuals, examine political decision-making, make findings where conduct may meet criminal thresholds, and refer cases for prosecution. Responses will be published. Silence will be recorded. The consultation closes soon. After that, the outcome is already set. Use the draft below. Do not deviate from it. Subject: Will you write to Anne Longfield on Inquiry powers and accountability? Dear [MP NAME], In 2013, Parliament’s Home Affairs Select Committee recorded that senior officials had failed in their duty of care to children subjected to organised sexual abuse. Those officials were identified. No prosecutions followed. Under section 5(5) of the Inquiries Act 2005, a statutory inquiry may act only within its Terms of Reference. Unless individual accountability and referral are explicitly required, an inquiry can avoid naming individuals or recommending criminal investigation. Will you write to Baroness Anne Longfield requesting that the Terms of Reference explicitly require the Inquiry to: - identify by name individuals whose acts or omissions may meet criminal thresholds, including misconduct in public office; and - refer such cases to the police and the Crown Prosecution Service. Please confirm, yes or no, whether you will do so. Yours sincerely, [NAME] _________ I need your help. My work is free. No paywalls. No gatekeeping. No exclusions. Because the truth shouldn’t belong only to those who can afford it. I’m Raja Miah MBE. For seven years, I led a campaign that exposed how senior Labour politicians helped protect Pakistani rape gangs and helped force a national inquiry. You won’t see me on the BBC. You won’t read my work in the legacy press. That’s not an accident. I take this to a place from where there is no coming back. I document everything in my newsletter. It’s 100% free to read. If this work matters to you, if you believe it must continue, I need your backing. 🔴 Supporting me costs as little as 75p a week (£30 a year): 👉 If you can’t do monthly, a one-off contribution genuinely helps keep this alive: 👉 👉 We’re up against a machine, politicians, police, officials, and media, working together to shrink, sanitise, and bury the truth. This work survives because of you. If you’ve ever shared my posts, learned something, or felt less alone reading them, stand with me. Raja 🙏

Raja Miah

11,114 просмотров • 5 месяцев назад