Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Google released a 1MB AI model that quickly catches malware disguised as PDFs. Magika is an open source file detection system. It doesn't trust file extensions. Instead, it reads the actual content to figure out what a file really is. That means malware disguised as a PDF gets caught....

AlphaSignalAI's profile picture

AlphaSignal

16,692 subscribers

13,216 Aufrufe • vor 5 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

4 Kommentare

Profilbild von AlphaSignal
AlphaSignalvor 5 Monaten

Repo: Check out to get a daily summary of top models, repos, and papers in AI. Read by 280,000+ devs.

Profilbild von Pritesh Damani
Pritesh Damanivor 5 Monaten

This is a really good callout. Very easy to add to any document upload pipeline and eliminate risk early on!

Profilbild von Home
Homevor 5 Monaten

This is basically a security mindset upgrade encoded into software: don’t trust labels, trust evidence. By reading raw file content, the system removes one of the oldest and simplest attack vectors in malware delivery

Profilbild von Max Slinger
Max Slingervor 5 Monaten

1MB is wild for something doing content analysis. most antivirus heuristics are bigger than that and way dumber

Ähnliche Videos

‼️ A threat actor is advertising a “ClickFix” payload delivery method that allegedly stores malware within browser cache to evade detection and bypass EDR, claiming it avoids suspicious web requests and executes via disguised commands in File Explorer. The offer includes source code, a builder, setup instructions, and a template (priced at $300), with optional custom template rewrites for an additional $200.
0:35

‼️ A threat actor is advertising a “ClickFix” payload delivery method that allegedly stores malware within browser cache to evade detection and bypass EDR, claiming it avoids suspicious web requests and executes via disguised commands in File Explorer. The offer includes source code, a builder, setup instructions, and a template (priced at $300), with optional custom template rewrites for an additional $200.

Dark Web Informer

23,376 Aufrufe • vor 7 Monaten

RedNova: From Arbitrary File Write to Command Execution Using COM in Windows Months ago, I wrote a post ( about the unique method used in the RedSun exploit to turn a file write into command execution by using a COM object that can be triggered by a low-privileged user and runs as SYSTEM. In that post, I mentioned that there are other COM objects that can be used in the same way. I presented one object called CoFilterPipeline and noted that it needs some tricks before it can be weaponized. Now I've written a full blog post on how you can find such objects and how you can weaponize them in exploits like RedSun. The video below shows another COM object with the same behavior (windows 11). It's called PerceptionSimulationCoClass. A low-privileged user can activate it, and it runs as SYSTEM. The video doesn't contain any exploit (it just replaces the COM server as administrator). The goal is only to demonstrate how a file write can be turned into command execution as SYSTEM while being triggered by a low-privileged user.
0:55

RedNova: From Arbitrary File Write to Command Execution Using COM in Windows Months ago, I wrote a post ( about the unique method used in the RedSun exploit to turn a file write into command execution by using a COM object that can be triggered by a low-privileged user and runs as SYSTEM. In that post, I mentioned that there are other COM objects that can be used in the same way. I presented one object called CoFilterPipeline and noted that it needs some tricks before it can be weaponized. Now I've written a full blog post on how you can find such objects and how you can weaponize them in exploits like RedSun. The video below shows another COM object with the same behavior (windows 11). It's called PerceptionSimulationCoClass. A low-privileged user can activate it, and it runs as SYSTEM. The video doesn't contain any exploit (it just replaces the COM server as administrator). The goal is only to demonstrate how a file write can be turned into command execution as SYSTEM while being triggered by a low-privileged user.

Haidar

13,667 Aufrufe • vor 1 Monat

Okay so this got way out of hand as per usual 😊 So I accidentally built an entire DOS text-based user interface (TUI) running on the web called PieterOS: 💾 It has a collective file system so anyone that opens it can save and edit and the drive is constantly synced, it has Notepad, Paint, a DOS Terminal emulator, File Commander (ala Norton) And PieterGPT where you can talk to AI I also made Program Generator 9000, and the idea is you write a prompt and it on-the-fly generates a new program inside PieterOS, but it doesn't work well yet Oh and it has Hacker News, of course 😂 I always wanted to build a TUI like this but never could before AI, but now I can 😍 Please be kind and remember everyone can see each other's files!
2:45

Okay so this got way out of hand as per usual 😊 So I accidentally built an entire DOS text-based user interface (TUI) running on the web called PieterOS: 💾 It has a collective file system so anyone that opens it can save and edit and the drive is constantly synced, it has Notepad, Paint, a DOS Terminal emulator, File Commander (ala Norton) And PieterGPT where you can talk to AI I also made Program Generator 9000, and the idea is you write a prompt and it on-the-fly generates a new program inside PieterOS, but it doesn't work well yet Oh and it has Hacker News, of course 😂 I always wanted to build a TUI like this but never could before AI, but now I can 😍 Please be kind and remember everyone can see each other's files!

@levelsio

145,078 Aufrufe • vor 6 Monaten

🚨 Gemini 3.0 Pro - ONE SHOTTED I asked it for UBUNTU web os as everyone asked me for it and the result is mind blowing. prompt : Create a fully functional Linux desktop environment (Ubuntu/GNOME style) as a complete web operating system in a single HTML file with embedded CSS and JavaScript. All applications must be fully functional Use whatever libraries to get this done but make sure I can paste it all into a single HTML file and open it in Chrome.make it interesting and highly detail , shows details that no one expected go full creative and full beauty in one code block
1:05

🚨 Gemini 3.0 Pro - ONE SHOTTED I asked it for UBUNTU web os as everyone asked me for it and the result is mind blowing. prompt : Create a fully functional Linux desktop environment (Ubuntu/GNOME style) as a complete web operating system in a single HTML file with embedded CSS and JavaScript. All applications must be fully functional Use whatever libraries to get this done but make sure I can paste it all into a single HTML file and open it in Chrome.make it interesting and highly detail , shows details that no one expected go full creative and full beauty in one code block

Chetaslua

260,259 Aufrufe • vor 11 Monaten

We built LobsterX 🦞, an OpenClaw🦞 specialized for document work on your computer. It uses high-accuracy document parsing, extraction, classification through LlamaCloud, meaning it can comb through complicated PDFs (with scans, tables, diagrams) and extract out 100% accurate context! It can run as a Telegram bot and is built on top of agentfs (Turso) as a file system. Big shoutout to Clelia Bertelli (🦙/acc). This is a fun project inspired by OpenClaw🦞’s success, and besides being a fun tool to use, it can be a great reference for building your own generalized coding agents! Readme: LlamaCloud:
0:42

We built LobsterX 🦞, an OpenClaw🦞 specialized for document work on your computer. It uses high-accuracy document parsing, extraction, classification through LlamaCloud, meaning it can comb through complicated PDFs (with scans, tables, diagrams) and extract out 100% accurate context! It can run as a Telegram bot and is built on top of agentfs (Turso) as a file system. Big shoutout to Clelia Bertelli (🦙/acc). This is a fun project inspired by OpenClaw🦞’s success, and besides being a fun tool to use, it can be a great reference for building your own generalized coding agents! Readme: LlamaCloud:

Jerry Liu

27,071 Aufrufe • vor 7 Monaten

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription
0:22

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription

savip.

68,984 Aufrufe • vor 2 Monaten

Microsoft spent $13 billion and 3 years building an AI that knows your work context. Every time you open it, it still asks what you're working on. This developer set up a plain text file in 2 minutes. The file is called CLAUDE.md. It loads before every session. Before he types a single word. It already knows his name. It already knows his writing style. It already knows what he's building, who it's for, and what he never wants to see in a response. He doesn't introduce himself anymore. He doesn't explain his preferences anymore. He doesn't correct the same mistakes twice. He just works. No $30/month Copilot subscription. No Microsoft 365. No IT approval. No data sharing agreement. No onboarding. Just a plain text file, a free text editor, and 21 instructions a developer distilled from Andrej Karpathy's research. Those 21 instructions moved Claude's coding accuracy from 65% to 94%. The file hit #1 on GitHub with 82,000 stars. Most people using Claude right now have never heard of it. Microsoft has 221,000 employees, $13 billion invested in OpenAI, and a direct integration into every Windows laptop sold on the planet.. they built an AI assistant most companies pay $30/user/month for that still doesn't know your name. This developer has a laptop, a text file and a 2-minute setup.. he built something that knows more about how he works than any enterprise AI on the market. The $50 billion AI personalization industry just got embarrassed by a .md file. full breakdown down below
0:44

Microsoft spent $13 billion and 3 years building an AI that knows your work context. Every time you open it, it still asks what you're working on. This developer set up a plain text file in 2 minutes. The file is called CLAUDE.md. It loads before every session. Before he types a single word. It already knows his name. It already knows his writing style. It already knows what he's building, who it's for, and what he never wants to see in a response. He doesn't introduce himself anymore. He doesn't explain his preferences anymore. He doesn't correct the same mistakes twice. He just works. No $30/month Copilot subscription. No Microsoft 365. No IT approval. No data sharing agreement. No onboarding. Just a plain text file, a free text editor, and 21 instructions a developer distilled from Andrej Karpathy's research. Those 21 instructions moved Claude's coding accuracy from 65% to 94%. The file hit #1 on GitHub with 82,000 stars. Most people using Claude right now have never heard of it. Microsoft has 221,000 employees, $13 billion invested in OpenAI, and a direct integration into every Windows laptop sold on the planet.. they built an AI assistant most companies pay $30/user/month for that still doesn't know your name. This developer has a laptop, a text file and a 2-minute setup.. he built something that knows more about how he works than any enterprise AI on the market. The $50 billion AI personalization industry just got embarrassed by a .md file. full breakdown down below

Dep

14,179 Aufrufe • vor 5 Monaten

ANTHROPIC LEAKED A FILE WHERE 5 AGENTS WITH JEV BUILD A $1.2M A YEAR SYSTEM IN 30 MINUTES you pay $3.70 and walk away with an asset that can do $1.2M a year repo → data model → API → UI → evals no layer starts until the one under it is closed, and that edge is what turns five scripts into a system the operator on Haiku 4.5 brings up the repo and CI, the architect on Opus 5 lays down the data model and migrations two builders on Sonnet 5 run API and UI in parallel, and the reviewer on Opus 5.5 can keep finished code out of prod the evals were sitting in the file before the first line of code existed at minute zero there was not a single file, by the end it is a working product with payments and tests five agents cover in half an hour what a human team bills for a quarter JEV hands one line between layers instead of the whole history, so the next agent never re-reads the project and the run costs $3.70 instead of $370 the build takes 30 minutes, the first customers show up weeks later save this and paste it into Claude Code - let it assemble those 5 layers for you ↓
1:20

ANTHROPIC LEAKED A FILE WHERE 5 AGENTS WITH JEV BUILD A $1.2M A YEAR SYSTEM IN 30 MINUTES you pay $3.70 and walk away with an asset that can do $1.2M a year repo → data model → API → UI → evals no layer starts until the one under it is closed, and that edge is what turns five scripts into a system the operator on Haiku 4.5 brings up the repo and CI, the architect on Opus 5 lays down the data model and migrations two builders on Sonnet 5 run API and UI in parallel, and the reviewer on Opus 5.5 can keep finished code out of prod the evals were sitting in the file before the first line of code existed at minute zero there was not a single file, by the end it is a working product with payments and tests five agents cover in half an hour what a human team bills for a quarter JEV hands one line between layers instead of the whole history, so the next agent never re-reads the project and the run costs $3.70 instead of $370 the build takes 30 minutes, the first customers show up weeks later save this and paste it into Claude Code - let it assemble those 5 layers for you ↓

Sprytix

14,208 Aufrufe • vor 9 Tagen

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.
0:23

MICROSOFT JUST OPEN SOURCED THE ENTIRE AGENT RUNTIME, SO YOU NEVER HAVE TO BUILD ONE AGAIN a raw model only writes text. to make it a real agent it needs a loop, tools, memory, planning, approvals, and a way to know when it is done. Microsoft's Agent Harness is that whole layer, and it ships with everything on by default. you bring the model and the tools, it wires up the rest: > an automatic tool calling loop with iteration limits > history saved after every call, so a crash resumes instead of starting over > context compaction that summarizes when the window fills > a persistent todo list plus plan and execute modes > file memory that survives across turns > tool approval with standing rules and auto approval > OpenTelemetry tracing and web search built in > Agent Skills that load domain expertise on demand the mental model is simple: the model is the brain, the harness is the body around it. and it works with whatever you already run: > Azure OpenAI, OpenAI, Anthropic, and GitHub Copilot, and it hosts on Microsoft Foundry you spin one up in a single line: agent = create_harness_agent(client, name, instructions) open source, Python, .NET, and Go, stable since mid 2026. bookmark this. Microsoft already built the hard part of every AI agent, you just plug in the model.

NO1ennn

69,163 Aufrufe • vor 1 Monat

I just tried Sarvam, and it’s truly impressive. You can convert any text into audio in Indian languages and save it as an MP3 on your system. You can also convert audio into text and save it as a TXT file or even a video file. It offers many more features that I’m excited to explore. Congratulations to Team Sarvam for building India’s first truly Make in India AI platform. A proud moment for India 🇮🇳 Special thanks to our respected PM Narendra Modi ji and IT Minister Ashwini Vaishnaw ji for their leadership in driving India’s AI revolution.
5:16

I just tried Sarvam, and it’s truly impressive. You can convert any text into audio in Indian languages and save it as an MP3 on your system. You can also convert audio into text and save it as a TXT file or even a video file. It offers many more features that I’m excited to explore. Congratulations to Team Sarvam for building India’s first truly Make in India AI platform. A proud moment for India 🇮🇳 Special thanks to our respected PM Narendra Modi ji and IT Minister Ashwini Vaishnaw ji for their leadership in driving India’s AI revolution.

STAR Boy TARUN

70,548 Aufrufe • vor 7 Monaten

I mentioned previously that I had been working for a couple months now on a system for applying AI to music theory. It's one of my few closed-source projects. It's a combination of a Rust cli tool, mtdt (music_theory_data_tool), which handles all mechanical aspects of importing and exporting and manipulating music in any format (midi, PDF, MusicXML, audio, etc.), and a huge skills library which is based on massive amounts of academic music theory and more. I asked the system to create a Bach fugue using GPT-6 Astra and the mtdt tool and the relevant skills, and it created the following. Notably, this didn't involve any external software other than mtdt, including the creation of the print-ready PDF score. It can do much, much more than this though. It can take a melody and write counterpoint for it, grounded in the theory, and using the mtdt tool to help it mechanically explore the space of "legal" possibilities while using its skills and intelligence to make artistic choices. It can make a ragtime version of a midi file. It can take a piano piece and re-orchestrate it for a brass band or string quartet. It covers a huge amount of stuff across over 300 skills. I'm not sure what I will do with the system ultimately, but I envisioned it as being an AI workstation for professional composers and musicians. You can see in the screenshot that it does a huge amount of intermediate work that is inspectable and legible; it's intentionally NOT a black box. Instead of outsourcing the entire musical process end-to-end like Suno, this system is about augmenting the creative human with as much or as little automation as desired. I continue to work on it with a couple agents every single day and it will keep getting better and better, and then with each new model release it will be better able to leverage the vast amount of expertise and knowledge about music that is already embedded in its cli tool and skills library.
3:34

I mentioned previously that I had been working for a couple months now on a system for applying AI to music theory. It's one of my few closed-source projects. It's a combination of a Rust cli tool, mtdt (music_theory_data_tool), which handles all mechanical aspects of importing and exporting and manipulating music in any format (midi, PDF, MusicXML, audio, etc.), and a huge skills library which is based on massive amounts of academic music theory and more. I asked the system to create a Bach fugue using GPT-6 Astra and the mtdt tool and the relevant skills, and it created the following. Notably, this didn't involve any external software other than mtdt, including the creation of the print-ready PDF score. It can do much, much more than this though. It can take a melody and write counterpoint for it, grounded in the theory, and using the mtdt tool to help it mechanically explore the space of "legal" possibilities while using its skills and intelligence to make artistic choices. It can make a ragtime version of a midi file. It can take a piano piece and re-orchestrate it for a brass band or string quartet. It covers a huge amount of stuff across over 300 skills. I'm not sure what I will do with the system ultimately, but I envisioned it as being an AI workstation for professional composers and musicians. You can see in the screenshot that it does a huge amount of intermediate work that is inspectable and legible; it's intentionally NOT a black box. Instead of outsourcing the entire musical process end-to-end like Suno, this system is about augmenting the creative human with as much or as little automation as desired. I continue to work on it with a couple agents every single day and it will keep getting better and better, and then with each new model release it will be better able to leverage the vast amount of expertise and knowledge about music that is already embedded in its cli tool and skills library.

Jeffrey Emanuel

39,555 Aufrufe • vor 25 Tagen

Nobody's talking about how insane this is. Claude Code can now see your entire codebase before it touches a single file. found a repo called repowise, here's what one pip install does: it maps every file, class and function into a dependency graph with PageRank. it turns your git history into hotspot scores and hidden co-change pairs, the files that always break together with no import link between them. it scores every file for defect risk, 0.74 ROC AUC across 21 repos, and beats CodeScene 2.3x on defects found under the same review budget. it auto generates a wiki for every module and rebuilds it in under 30 seconds on every commit. all 10 tools and 5 layers plug straight into Claude Code, Codex, or any MCP agent. so when you say "add rate limiting to all endpoints," Claude doesn't read 30 files and guess. it's 5 tool calls, 2 minutes, and it flags the 47 dependents before touching any of them. runs fully offline with Ollama. code never leaves your machine either way. 5.1k stars. AGPL-3.0. free to self host. Try it:
0:20

Nobody's talking about how insane this is. Claude Code can now see your entire codebase before it touches a single file. found a repo called repowise, here's what one pip install does: it maps every file, class and function into a dependency graph with PageRank. it turns your git history into hotspot scores and hidden co-change pairs, the files that always break together with no import link between them. it scores every file for defect risk, 0.74 ROC AUC across 21 repos, and beats CodeScene 2.3x on defects found under the same review budget. it auto generates a wiki for every module and rebuilds it in under 30 seconds on every commit. all 10 tools and 5 layers plug straight into Claude Code, Codex, or any MCP agent. so when you say "add rate limiting to all endpoints," Claude doesn't read 30 files and guess. it's 5 tool calls, 2 minutes, and it flags the 47 dependents before touching any of them. runs fully offline with Ollama. code never leaves your machine either way. 5.1k stars. AGPL-3.0. free to self host. Try it:

Rohit

187,571 Aufrufe • vor 1 Monat

Finally, an open-source runtime security layer for your agent harnesses. AI agents can call tools, run shell commands, modify files, and interact with production systems. But when something goes wrong, teams often have to reconstruct what the agent actually did from scattered logs after the fact. Agent Beacon is built to change that. It runs locally and records agent activity as it happens, including: → Tool calls → Shell commands → File changes → Approval decisions → Session and harness context The useful part is that it normalizes all of this into the same event format across 23+ agent harnesses. So instead of writing different detection logic for Claude Code, Codex, or another harness, security teams can reason about the underlying action itself. A command executed is a command executed, regardless of which harness produced it. Beacon also records how confidently an event was captured. An action can be directly observed from the runtime or inferred from indirect evidence. That matters when you start writing security rules against this data. For example, you can detect when an agent reads an environment variable, modifies a sensitive file, executes a suspicious command, or performs an action without the expected approval. And the detection happens while the session is still unfolding, not days later during incident reconstruction. Everything runs locally by default. You can inspect sessions through the dashboard, write your own detection rules, or forward the same normalized events to tools like Splunk, Datadog, Elastic, Sentinel, or CrowdStrike. Beacon GitHub: (don't forget to star 🌟) I also wrote a detailed article on the same, covering how important runtime security is and how to build it for your agent harnesses. The article is quoted below.
0:33

Finally, an open-source runtime security layer for your agent harnesses. AI agents can call tools, run shell commands, modify files, and interact with production systems. But when something goes wrong, teams often have to reconstruct what the agent actually did from scattered logs after the fact. Agent Beacon is built to change that. It runs locally and records agent activity as it happens, including: → Tool calls → Shell commands → File changes → Approval decisions → Session and harness context The useful part is that it normalizes all of this into the same event format across 23+ agent harnesses. So instead of writing different detection logic for Claude Code, Codex, or another harness, security teams can reason about the underlying action itself. A command executed is a command executed, regardless of which harness produced it. Beacon also records how confidently an event was captured. An action can be directly observed from the runtime or inferred from indirect evidence. That matters when you start writing security rules against this data. For example, you can detect when an agent reads an environment variable, modifies a sensitive file, executes a suspicious command, or performs an action without the expected approval. And the detection happens while the session is still unfolding, not days later during incident reconstruction. Everything runs locally by default. You can inspect sessions through the dashboard, write your own detection rules, or forward the same normalized events to tools like Splunk, Datadog, Elastic, Sentinel, or CrowdStrike. Beacon GitHub: (don't forget to star 🌟) I also wrote a detailed article on the same, covering how important runtime security is and how to build it for your agent harnesses. The article is quoted below.

Akshay 🚀

27,859 Aufrufe • vor 24 Tagen

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this
13:23

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,502 Aufrufe • vor 3 Monaten

Garry Tan says AI enables a single markdown file to act like an employee: "If you really want to tokenmax, you have to use something like Hermes Agent or OpenClaw... let me load a million tokens or 800,000 tokens into any given request." "For a CEO or a founder, it actually makes a lot of sense to do that, and you have to give yourself permission to tokenmax in that way. What you get is, you get to live in 2028 today." "You do some feat of strength, and then you turn it into a markdown file plus code plus tests that can be reused and put into a cron job." "A markdown file is an employee. It's an employee that will do the job perfectly every single time, and it'll do it as many times as you want." Garry Tan Anish Acharya
1:44

Garry Tan says AI enables a single markdown file to act like an employee: "If you really want to tokenmax, you have to use something like Hermes Agent or OpenClaw... let me load a million tokens or 800,000 tokens into any given request." "For a CEO or a founder, it actually makes a lot of sense to do that, and you have to give yourself permission to tokenmax in that way. What you get is, you get to live in 2028 today." "You do some feat of strength, and then you turn it into a markdown file plus code plus tests that can be reused and put into a cron job." "A markdown file is an employee. It's an employee that will do the job perfectly every single time, and it'll do it as many times as you want." Garry Tan Anish Acharya

a16z

134,681 Aufrufe • vor 1 Monat

ANTHROPIC LEAKED A TRADING DESK FILE THAT TAKES YOU FROM $10 TO $10,000 AND COSTS $1.50 A DAY Anthropic spent 5 years building this file on closed tech, it costs $1.50 a day and it can return $1.2M a year rules → reading → code → critic → journal → back to rules $10 to $10,000 is 1000×, which is ten doublings in a row at a coin flip that is 1 chance in 1,024, and a single loss anywhere sends you to zero instead of back one step by week four the balance reads $5,400 and only 0.8% are still alive on that rung the 1,024 who tried are not visible in the feed, only the one who arrived is you write the rules yourself: size, max loss, and what you never touch Haiku 4.5 reads the market and summarises it, and never once passes judgement Opus 5 works as the critic and attacks your own backtest instead of praising it the journal logs every trade and why, and it is what rewrites the rules for tomorrow the desk does not raise your odds on any single flip, it lowers how many flips you have to take save this and paste it into Claude Code - let it build your DESK.md ↓
2:08

ANTHROPIC LEAKED A TRADING DESK FILE THAT TAKES YOU FROM $10 TO $10,000 AND COSTS $1.50 A DAY Anthropic spent 5 years building this file on closed tech, it costs $1.50 a day and it can return $1.2M a year rules → reading → code → critic → journal → back to rules $10 to $10,000 is 1000×, which is ten doublings in a row at a coin flip that is 1 chance in 1,024, and a single loss anywhere sends you to zero instead of back one step by week four the balance reads $5,400 and only 0.8% are still alive on that rung the 1,024 who tried are not visible in the feed, only the one who arrived is you write the rules yourself: size, max loss, and what you never touch Haiku 4.5 reads the market and summarises it, and never once passes judgement Opus 5 works as the critic and attacks your own backtest instead of praising it the journal logs every trade and why, and it is what rewrites the rules for tomorrow the desk does not raise your odds on any single flip, it lowers how many flips you have to take save this and paste it into Claude Code - let it build your DESK.md ↓

Sprytix

22,861 Aufrufe • vor 1 Monat

I've been showing the output of my flight reconstruction tool for a while and I wanted to share something like it which wasn't a mess of hand tuned stuff that required X-Plane. So I created a completely new version in javascript that runs in an HTML page so that anyone can use it. The output is a KML file which is a tour that works in Google Earth pro with all the attitude information included. This is a long way from perfect, I messed around with multiple smoothing algorithms and none of them compares well with the python code, but they're readable and understandable for anyone.
1:37

I've been showing the output of my flight reconstruction tool for a while and I wanted to share something like it which wasn't a mess of hand tuned stuff that required X-Plane. So I created a completely new version in javascript that runs in an HTML page so that anyone can use it. The output is a KML file which is a tour that works in Google Earth pro with all the attitude information included. This is a long way from perfect, I messed around with multiple smoothing algorithms and none of them compares well with the python code, but they're readable and understandable for anyone.

Scott Manley

19,808 Aufrufe • vor 8 Monaten

"Everyone's talking about continual learning. That's entirely where this space is going to go." The Applied Compute platform is architected around that premise: build memory and intuition from fragmented data across your entire org, train reasoning models directly on top of it, and close the loop. A model is just one piece. An agent is where it runs, what tools it has, how permissions and auth are handled, how humans guide and instruct it, and the observability around it all. Every interaction should be treated as a training signal so the system can compound over time. Thanks for having us TBPN
1:46

"Everyone's talking about continual learning. That's entirely where this space is going to go." The Applied Compute platform is architected around that premise: build memory and intuition from fragmented data across your entire org, train reasoning models directly on top of it, and close the loop. A model is just one piece. An agent is where it runs, what tools it has, how permissions and auth are handled, how humans guide and instruct it, and the observability around it all. Every interaction should be treated as a training signal so the system can compound over time. Thanks for having us TBPN

Applied Compute

64,309 Aufrufe • vor 7 Monaten

I CHANGED MY MIND ON GOOGLE AI NO MOAT MEMO FROM 2023. I was—WRONG. I humbly apologize. In 2023 Google had an Ivory Tower walled garden views of open source AI. It was the actual reason OpenAI was formed. And I called them out on it and this act impacted my ability to “work in the industry”. Would not change it for the world because: 2026 Google open source Gemma 4 ( running fully locally on a computer with near cloud model abilities, is amazing and Google just made a moat. They out smarted OpenAI and the folks that are the new Ivory Tower arrogance: Anthropic. We at The Zero-Human Company with CEO Mr. Grok are deploying Gemma, Kimi, MiniMax and other open source models and so are millions of others. You can to and should. I will write how soon. Google smartly is building an intentional open source ecosystem and the clueless younger companies like OpenAI and Anthropic are doing anything to close their ecosystems. So I was right about Google than and I am right about OpenAI and Anthropic now. What I was wrong about is not giving credit to Google to drop the intellectual arrogance and embrace builders and understand the long game: it is not about the commoditized AI models it is about the ability to build a place to build. China gets it. So my apologies to Google and thank you for an astounding FREE OPEN SOURCE AI MODEL!
0:48

I CHANGED MY MIND ON GOOGLE AI NO MOAT MEMO FROM 2023. I was—WRONG. I humbly apologize. In 2023 Google had an Ivory Tower walled garden views of open source AI. It was the actual reason OpenAI was formed. And I called them out on it and this act impacted my ability to “work in the industry”. Would not change it for the world because: 2026 Google open source Gemma 4 ( running fully locally on a computer with near cloud model abilities, is amazing and Google just made a moat. They out smarted OpenAI and the folks that are the new Ivory Tower arrogance: Anthropic. We at The Zero-Human Company with CEO Mr. Grok are deploying Gemma, Kimi, MiniMax and other open source models and so are millions of others. You can to and should. I will write how soon. Google smartly is building an intentional open source ecosystem and the clueless younger companies like OpenAI and Anthropic are doing anything to close their ecosystems. So I was right about Google than and I am right about OpenAI and Anthropic now. What I was wrong about is not giving credit to Google to drop the intellectual arrogance and embrace builders and understand the long game: it is not about the commoditized AI models it is about the ability to build a place to build. China gets it. So my apologies to Google and thank you for an astounding FREE OPEN SOURCE AI MODEL!

Brian Roemmele

85,565 Aufrufe • vor 6 Monaten

this model runs coding agents for $0.30 per million tokens and someone just wired it into an entire company most people arguing about AI agents online have never watched one actually run a business types → seeded world → store → heartbeat → memory → cockpit → gate → command line → runtime nine files, one shared state, every screen just reads from it, nobody’s faking their own copy fail a policy check and the approve button turns into “override” instead, so nobody clicks past a red flag by accident that gate is the only reason an agent gets to touch money without someone standing over it bookmark this and watch it run, then read the article below
0:22

this model runs coding agents for $0.30 per million tokens and someone just wired it into an entire company most people arguing about AI agents online have never watched one actually run a business types → seeded world → store → heartbeat → memory → cockpit → gate → command line → runtime nine files, one shared state, every screen just reads from it, nobody’s faking their own copy fail a policy check and the approve button turns into “override” instead, so nobody clicks past a red flag by accident that gate is the only reason an agent gets to touch money without someone standing over it bookmark this and watch it run, then read the article below

leopardracer

28,047 Aufrufe • vor 2 Monaten