正在加载视频...

视频加载失败

返回首页

‼️Copy Fail (CVE-2026-31431) is a Linux privilege escalation bug that lets any local user get root using a 732-byte Python script, and itworks on basically every major Linux distro shipped since 2017. Website: Write-up: GitHub: It's a logic flaw in the kernel's crypto code (authencesn via AF_ALG and splice())...

DarkWebInformer's profile picture

Dark Web Informer

223,919 subscribers

444,679 次观看 • 3 个月前 •via X (Twitter)

新闻政治教育科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

This is how you deal with corruption and a Government despised by its people A Government that does everything it can to go crawling to Brussels ignoring the plight of its own citizens in Ireland. Rise up Britain you too can be like the Republic It can't go on like this!
0:17

This is how you deal with corruption and a Government despised by its people A Government that does everything it can to go crawling to Brussels ignoring the plight of its own citizens in Ireland. Rise up Britain you too can be like the Republic It can't go on like this!

Make Britain Great Again

90,482 次观看 • 3 个月前

I just built a Claude Code skill that scores whether your landing page actually keeps your Meta ad's promise 🤯 Drop in your ad and the page it points to. It reads both, scores the "ad scent" from click to page, and finds the exact line where the page breaks the promise that won the click. All inside Claude Code. Perfect for DTC brands and media buyers who pour everything into the ad and the CPA but never grade the seam in between. If you're scaling spend on a winning ad, the click is landing on a page that opens with something slightly different, the ad promised 50% off and the page shows full price, the ad hooked "for oily skin" and the page is a generic homepage, and nothing looks broken, but the visitor feels it and bounces... That gap has a name in conversion work: message match. And you already paid for the click you're losing. Here's what it does: → Drop in your ad (headline, copy, offer, CTA) and the landing-page URL → It fetches the live page and reads what's actually above the fold → Grades 7 continuity dimensions: promise, offer, angle, CTA, audience, proof, visual → Shows your ad's words next to your page's words, so every gap is right there → Rewrites your hero headline so the page keeps the ad's promise → Renders a dashboard with a Match Score out of 100 No guessing why the click bounced. No blaming the creative for a page problem. No buying more traffic to fix a copy problem. What you get: → A Match Score on every ad-to-page pair before you scale → The ad-side vs page-side quotes, side by side, for every leak → A hero rewrite you can paste straight onto the page → A dashboard you can hand to your team or client I'm giving away the full skill completely for free. Built 100% in Claude Code. No API keys. Want the skill? > Like this post > Comment "MATCH" And I'll send it over (must be following so I can DM)
0:14

I just built a Claude Code skill that scores whether your landing page actually keeps your Meta ad's promise 🤯 Drop in your ad and the page it points to. It reads both, scores the "ad scent" from click to page, and finds the exact line where the page breaks the promise that won the click. All inside Claude Code. Perfect for DTC brands and media buyers who pour everything into the ad and the CPA but never grade the seam in between. If you're scaling spend on a winning ad, the click is landing on a page that opens with something slightly different, the ad promised 50% off and the page shows full price, the ad hooked "for oily skin" and the page is a generic homepage, and nothing looks broken, but the visitor feels it and bounces... That gap has a name in conversion work: message match. And you already paid for the click you're losing. Here's what it does: → Drop in your ad (headline, copy, offer, CTA) and the landing-page URL → It fetches the live page and reads what's actually above the fold → Grades 7 continuity dimensions: promise, offer, angle, CTA, audience, proof, visual → Shows your ad's words next to your page's words, so every gap is right there → Rewrites your hero headline so the page keeps the ad's promise → Renders a dashboard with a Match Score out of 100 No guessing why the click bounced. No blaming the creative for a page problem. No buying more traffic to fix a copy problem. What you get: → A Match Score on every ad-to-page pair before you scale → The ad-side vs page-side quotes, side by side, for every leak → A hero rewrite you can paste straight onto the page → A dashboard you can hand to your team or client I'm giving away the full skill completely for free. Built 100% in Claude Code. No API keys. Want the skill? > Like this post > Comment "MATCH" And I'll send it over (must be following so I can DM)

Mike Futia

10,548 次观看 • 22 天前

The problem with civnats (a term I’ll stop using in 2026 as it just means neoliberal) is that they act tough and say things like “deport all the criminals and terrorists” but the obvious flaw with that is we don’t know someone is going to becoming a criminal or terrorist until after the act has already been committed. So if you want to end things like stabbing sprees, terrorism, and machete gangs you have to identify the groups doing it (e.g. blacks and Muslims) and apply some level of ethnicity based deportations. Even if you didn’t want blanket remigration you won’t be able to eliminate the problem without making ethnicity and religion a major factor in deportations. I know Konstantin Kisin is smart enough to realise this which makes his motivations for not admitting it suspect but I do believe that Andrew Gold is just a dim toff getting by based on an accent and old boys network.
0:18

The problem with civnats (a term I’ll stop using in 2026 as it just means neoliberal) is that they act tough and say things like “deport all the criminals and terrorists” but the obvious flaw with that is we don’t know someone is going to becoming a criminal or terrorist until after the act has already been committed. So if you want to end things like stabbing sprees, terrorism, and machete gangs you have to identify the groups doing it (e.g. blacks and Muslims) and apply some level of ethnicity based deportations. Even if you didn’t want blanket remigration you won’t be able to eliminate the problem without making ethnicity and religion a major factor in deportations. I know Konstantin Kisin is smart enough to realise this which makes his motivations for not admitting it suspect but I do believe that Andrew Gold is just a dim toff getting by based on an accent and old boys network.

Wolf 🐺

33,615 次观看 • 7 个月前

Claude Design + Shopify is f*cking ridiculous 🤯 You can now publish pages from Claude Design → Claude Code → Shopify. Built 100% with Claude Design, Claude Code, and the Shopify CLI. Perfect for DTC brands and agencies who want to skip the design → dev handoff entirely. Here's how it works: → Design any landing page in Claude Design → Export as a zip and drop it into Claude Code → Install the Shopify + Shopify AI Toolkit plugins → Prompt Claude to convert the HTML into a Shopify page template + push to live theme → Claude uploads the images, deploys the files, and creates a published page No more handing designs off to a dev and waiting 2 weeks for a Shopify page. What you get: - A workflow that turns any Claude Design page into a real Shopify page template - Editable sections so your marketing team can swap copy, images, and CTAs without code - Images uploaded straight to Shopify Files automatically - A files-only deploy that only touches what's new in your live theme - A repeatable pipeline you can use every time you design a new landing page This is essentially the design-to-deploy pipeline brands have been waiting for. I put together a step-by-step playbook for going from Claude Design → published Shopify page. Every install, every plugin, every command, and the exact prompt that runs the whole thing. Want the playbook for free? > Like this post > Comment "SHOP" And I'll send it over (must be following so I can DM)
0:17

Claude Design + Shopify is f*cking ridiculous 🤯 You can now publish pages from Claude Design → Claude Code → Shopify. Built 100% with Claude Design, Claude Code, and the Shopify CLI. Perfect for DTC brands and agencies who want to skip the design → dev handoff entirely. Here's how it works: → Design any landing page in Claude Design → Export as a zip and drop it into Claude Code → Install the Shopify + Shopify AI Toolkit plugins → Prompt Claude to convert the HTML into a Shopify page template + push to live theme → Claude uploads the images, deploys the files, and creates a published page No more handing designs off to a dev and waiting 2 weeks for a Shopify page. What you get: - A workflow that turns any Claude Design page into a real Shopify page template - Editable sections so your marketing team can swap copy, images, and CTAs without code - Images uploaded straight to Shopify Files automatically - A files-only deploy that only touches what's new in your live theme - A repeatable pipeline you can use every time you design a new landing page This is essentially the design-to-deploy pipeline brands have been waiting for. I put together a step-by-step playbook for going from Claude Design → published Shopify page. Every install, every plugin, every command, and the exact prompt that runs the whole thing. Want the playbook for free? > Like this post > Comment "SHOP" And I'll send it over (must be following so I can DM)

Mike Futia

57,469 次观看 • 2 个月前

🚨 BREAKING - The Panama Meteorite / Venom Creature [ ENCHANCED] - This is the latest video that the Man ( KinPanama on Tiktok) who found a meteorite in Panama, where a Venon symbiote like creature emerged from it. The user has said he was forced to say that the videos are for entertainment only and now he has removed the claims and is Bio and back to recording it again, it has grown in to a small sized Cat with and moving with its black Goo like tentacles. What do you think about this, this has been digitally enchanced by me for better visibility What do you think? #Ufotwitter
0:13

🚨 BREAKING - The Panama Meteorite / Venom Creature [ ENCHANCED] - This is the latest video that the Man ( KinPanama on Tiktok) who found a meteorite in Panama, where a Venon symbiote like creature emerged from it. The user has said he was forced to say that the videos are for entertainment only and now he has removed the claims and is Bio and back to recording it again, it has grown in to a small sized Cat with and moving with its black Goo like tentacles. What do you think about this, this has been digitally enchanced by me for better visibility What do you think? #Ufotwitter

T R U T H P O L E

1,790,042 次观看 • 10 个月前

This is Poltava, Ukraine. Zelensky’s special squads rounded up men on the street like stray dogs and locked them in a cage, after which they will be forcibly sent to the front lines. Yes, you heard that right — not a prison, but an actual cage for captured people. Meaghan Mobbs , what’s your take on this? You never miss a chance to write about Putin (as if anyone in the world doesn’t already know he’s a monster and a tyrant), yet when it comes to Zelensky and Yermak, you only write good things. Do you think this is normal? Does this look like a country of Western civilization and democracy to you? President Donald J. Trump Donald J. Trump JD Vance Marco Rubio Steve Witkoff
0:18

This is Poltava, Ukraine. Zelensky’s special squads rounded up men on the street like stray dogs and locked them in a cage, after which they will be forcibly sent to the front lines. Yes, you heard that right — not a prison, but an actual cage for captured people. Meaghan Mobbs , what’s your take on this? You never miss a chance to write about Putin (as if anyone in the world doesn’t already know he’s a monster and a tyrant), yet when it comes to Zelensky and Yermak, you only write good things. Do you think this is normal? Does this look like a country of Western civilization and democracy to you? President Donald J. Trump Donald J. Trump JD Vance Marco Rubio Steve Witkoff

Denys Yelisevych

27,742 次观看 • 11 个月前

Inviting early testers and contributors to Project Devika - The open-source alternative to Devin. 👩‍💻 As of now, Devika is far from the capabilities of Devin... but we'll eventually get there. So I am calling the open-source community to join forces! ❤️ Features: - 12 Agentic models that can interact with each other in a feedback loop to understand, browse, research, code, document, and make decisions according to the user's query to complete a project. - Supports Claude 3, GPT-4, GPT-3.5, and Local LLMs via ollama. - Devika can run the code she writes and fix/patch the code herself if she encounters any errors without user intervention. - Devika can deploy static websites she creates on Netlify. (Experimental) - And much more... Will be doing an official launch after intensive testing and bug fixes. 🙌 I've created a Discord server for the early testers and contributors. If you're interested in joining the team, reply to this tweet and I will DM you the invite link. #buildinpublic
0:19

Inviting early testers and contributors to Project Devika - The open-source alternative to Devin. 👩‍💻 As of now, Devika is far from the capabilities of Devin... but we'll eventually get there. So I am calling the open-source community to join forces! ❤️ Features: - 12 Agentic models that can interact with each other in a feedback loop to understand, browse, research, code, document, and make decisions according to the user's query to complete a project. - Supports Claude 3, GPT-4, GPT-3.5, and Local LLMs via ollama. - Devika can run the code she writes and fix/patch the code herself if she encounters any errors without user intervention. - Devika can deploy static websites she creates on Netlify. (Experimental) - And much more... Will be doing an official launch after intensive testing and bug fixes. 🙌 I've created a Discord server for the early testers and contributors. If you're interested in joining the team, reply to this tweet and I will DM you the invite link. #buildinpublic

mufeed vh

155,020 次观看 • 2 年前

THIS DEVELOPER USED OPENCLAW AGENTS TO RUN HIS B2B BUSINESS VIA TELEGRAM AND MADE $15,000/MONTH he doesn't write prompts from scratch or use generic browser interfaces. he runs a multi-agent framework through a mobile chat. the agents write code, test deployments, and update sites in real-time while he just hits approve the setup is straightforward: - spin up Coolify on a free cloud instance to host your own self-hosted agent panels - link the agent loop to a Telegram gateway to approve code edits from your phone - deploy specialized skill files directly to limit token waste and context decay - containerize the terminal execution using Docker to prevent security breaches if you are still running local agents without container safety, you are leaving money on the table. read the 30-day battle between OpenClaw and Hermes Agent to see who actually wins in production Full breakdown and migration playbook ↓
0:17

THIS DEVELOPER USED OPENCLAW AGENTS TO RUN HIS B2B BUSINESS VIA TELEGRAM AND MADE $15,000/MONTH he doesn't write prompts from scratch or use generic browser interfaces. he runs a multi-agent framework through a mobile chat. the agents write code, test deployments, and update sites in real-time while he just hits approve the setup is straightforward: - spin up Coolify on a free cloud instance to host your own self-hosted agent panels - link the agent loop to a Telegram gateway to approve code edits from your phone - deploy specialized skill files directly to limit token waste and context decay - containerize the terminal execution using Docker to prevent security breaches if you are still running local agents without container safety, you are leaving money on the table. read the 30-day battle between OpenClaw and Hermes Agent to see who actually wins in production Full breakdown and migration playbook ↓

marfin

26,654 次观看 • 1 个月前

i'm not fine after reading this a guy with a laptop got his own silicon chip manufactured with software Google gave away. the commercial version of that software rents for up to $1,000,000 a year. he never signed a vendor contract and never paid for a seat. he wrote the logic, pushed it to GitHub, and nine months later a wafer came out of a fab. getting silicon with your name in it used to take a company. now it takes nine months. his slot was 160 by 100 microns: about 1,000 logic gates, 8 inputs, 8 outputs, clocked past 50 MHz. more than 600 designs have already come back this way. this is the open silicon stack. Google and SkyWater published a complete 130nm manufacturing process, DARPA funded the software that turns code into a fab-ready file, and all of it sits in public repositories. turns out the whole flow fits in a git push: - write the logic in Verilog, or drag gates around in a browser if you have never done this - push to GitHub, an action runs synthesis, placement, routing and sign-off on the commit - OpenROAD finishes place-and-route with no human in the loop, code to fab file inside 24 hours - SKY130 carries the fab's real design rules, so passing the checks means it is manufacturable - a few hundred designs share one wafer, which is the only reason a person can afford the masks nobody puts this part in the thread: 130nm is roughly where the industry stood in 2001, and you wait six to nine months for silicon. this does not get you a GPU. it gets you a real object with your logic inside it. bookmark this. the video is one of those designs opened layer by layer, and every rectangle in it exists in the file that was sent to the fab.
0:16

i'm not fine after reading this a guy with a laptop got his own silicon chip manufactured with software Google gave away. the commercial version of that software rents for up to $1,000,000 a year. he never signed a vendor contract and never paid for a seat. he wrote the logic, pushed it to GitHub, and nine months later a wafer came out of a fab. getting silicon with your name in it used to take a company. now it takes nine months. his slot was 160 by 100 microns: about 1,000 logic gates, 8 inputs, 8 outputs, clocked past 50 MHz. more than 600 designs have already come back this way. this is the open silicon stack. Google and SkyWater published a complete 130nm manufacturing process, DARPA funded the software that turns code into a fab-ready file, and all of it sits in public repositories. turns out the whole flow fits in a git push: - write the logic in Verilog, or drag gates around in a browser if you have never done this - push to GitHub, an action runs synthesis, placement, routing and sign-off on the commit - OpenROAD finishes place-and-route with no human in the loop, code to fab file inside 24 hours - SKY130 carries the fab's real design rules, so passing the checks means it is manufacturable - a few hundred designs share one wafer, which is the only reason a person can afford the masks nobody puts this part in the thread: 130nm is roughly where the industry stood in 2001, and you wait six to nine months for silicon. this does not get you a GPU. it gets you a real object with your logic inside it. bookmark this. the video is one of those designs opened layer by layer, and every rectangle in it exists in the file that was sent to the fab.

Argona

147,809 次观看 • 6 天前

🤩 I just learned a super cool trick! Do you know how sometimes you want to record while you scroll on a website, like for a demo or something... But by using the mouse to scroll it turns out to be kinda janky and it doesn't look very good? No? Just me? 🤭 Well, I found out that if you paste this code in the console of your browser: ` setInterval(() => window.scrollBy(0, 4), 16); ` You can make the browser automatically scroll for you! And it looks super cool in the recording! 😎
0:12

🤩 I just learned a super cool trick! Do you know how sometimes you want to record while you scroll on a website, like for a demo or something... But by using the mouse to scroll it turns out to be kinda janky and it doesn't look very good? No? Just me? 🤭 Well, I found out that if you paste this code in the console of your browser: ` setInterval(() => window.scrollBy(0, 4), 16); ` You can make the browser automatically scroll for you! And it looks super cool in the recording! 😎

Florin Pop 👨🏻‍💻

29,839 次观看 • 10 个月前

Every website you’ve ever used is broken in a way you never noticed and it’s been this way for 30 years... A Midjourney engineer finally just fixed it. It’s called Pretext: A tiny library that lets websites lay out text the way magazines and newspapers do, with text flowing around images, wrapping into columns, and fitting perfectly into any shape, all at 120fps. This has been basically impossible on the web for 30 years. Every website you’ve ever used relies on the same clunky system from the 90s to figure out where text goes on screen. Pretext bypasses it entirely. 500x faster. The demos look like they shouldn’t be possible in a browser. Go look.
0:12

Every website you’ve ever used is broken in a way you never noticed and it’s been this way for 30 years... A Midjourney engineer finally just fixed it. It’s called Pretext: A tiny library that lets websites lay out text the way magazines and newspapers do, with text flowing around images, wrapping into columns, and fitting perfectly into any shape, all at 120fps. This has been basically impossible on the web for 30 years. Every website you’ve ever used relies on the same clunky system from the 90s to figure out where text goes on screen. Pretext bypasses it entirely. 500x faster. The demos look like they shouldn’t be possible in a browser. Go look.

Josh Kale

1,020,636 次观看 • 4 个月前

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️
0:16

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️

John McBride

150,334 次观看 • 5 个月前

The IRS is giving you a 100% write-off for buying Bitcoin miners? Under current tax law, Bitcoin mining hardware qualifies for 100% bonus depreciation. That means if you are a business owner or investor, you can write off the entire cost of your miners this year. Keep in mind, it is for the year they are placed in service. So if you are planning to capture a deduction on your April 2027 tax bill, your miners need to be hashing prior to December 31, 2026. If you have capital gains, passive income, or just a big tax bill, this is one of the most sophisticated ways to achieve a write-off and achieve Bitcoin exposure. If you are serious about building wealth and reducing your tax burden, this is the move.
0:12

The IRS is giving you a 100% write-off for buying Bitcoin miners? Under current tax law, Bitcoin mining hardware qualifies for 100% bonus depreciation. That means if you are a business owner or investor, you can write off the entire cost of your miners this year. Keep in mind, it is for the year they are placed in service. So if you are planning to capture a deduction on your April 2027 tax bill, your miners need to be hashing prior to December 31, 2026. If you have capital gains, passive income, or just a big tax bill, this is one of the most sophisticated ways to achieve a write-off and achieve Bitcoin exposure. If you are serious about building wealth and reducing your tax burden, this is the move.

Simple Mining

179,465 次观看 • 6 个月前

Stanford researchers did it again. They just built the agent-native version of Git. When an agent works on a longer task, the run builds up a lot of state. This includes files edited/created, a dev server, a database, installed packages, KV cache, etc. Say the agent is at step 10 and makes a mistake, maybe it misreads a traceback and rewrites a file that was actually fine. The tests start failing, and the run goes off track, although everything through step eight was correct. By default, the agent just tries to fix it, which creates more edits and tool calls. This burns more tokens and grows the context. The other options are a person stepping in to redirect it or restarting the whole run from step one. That's wasteful, because it pays for every model/tool call again and re-prefills the context. Moreover, since an agent's run is non-deterministic, it doesn't reproduce the same early steps anyway. The reason it's hard to just jump back exactly to a previous correct step and resume from there is that the trajectory is only a message log. It records what the agent said and which tools it called, but not the live state underneath. That state includes things like memory, open file handles, child processes, installed packages, /tmp, and KV cache. None of that is in the log. Git can version the files, but it doesn't snapshot the running process or the KV cache. Checking out step eight moves the files back, but the process is still sitting in step-ten memory with a cold cache. Shepherd is a runtime layer by Stanford that records the run as a trace of typed events rather than a flat log. Each agent-environment interaction becomes a commit, similar to Git, but it tracks the live run. Its commit includes the agent process and the filesystem together, copy-on-write, so a branch carries the actual state and not just the files. Going back to a previous step is then a single call that forks from that commit and continues from the exact state. The copy-on-write fork is roughly five times faster than docker commit, and because the prompt prefix through step eight is unchanged, the KV cache is reused over 95% on replay, so early steps aren't reprocessed again. Once the run can be forked, a meta-agent can sit on top and operate it. It watches the trace and reverts as soon as it looks wrong, before the bad write is committed. In practice, it's just Python calling fork, replay, and revert on the trace, rather than a separate control plane wired into the harness. Not everything is reversible though. Files and sandbox changes undo themselves, but a database write has no automatic undo, so it needs a matching undo step set up in advance. Something external, like a sent email or a real charge, can't be undone, so the supervisor's job there is to catch it before it fires. They tested this on a few public benchmarks. On CooperBench, where two agents work on the same codebase, adding a live supervisor took the pair-coding pass rate from 28.8% to 54.7%. It's still early and labeled alpha. The benefit mostly shows up when a run gets branched a lot over a heavy sandbox state, which is exactly where restarting wastes the most tokens and time. If Git was made to make file changes reversible, Shepherd is trying to do the same thing for a live agent run. Shepherd Repo: (don't forget to star it ⭐ ) That said, Shepherd reverts a bad step inside a run. The harness around it, the prompts, tools, and checks the supervisor relies on, still drifts across runs as models and dependencies change. Akshay wrote about making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it can't recur. Read it below.
0:15

Stanford researchers did it again. They just built the agent-native version of Git. When an agent works on a longer task, the run builds up a lot of state. This includes files edited/created, a dev server, a database, installed packages, KV cache, etc. Say the agent is at step 10 and makes a mistake, maybe it misreads a traceback and rewrites a file that was actually fine. The tests start failing, and the run goes off track, although everything through step eight was correct. By default, the agent just tries to fix it, which creates more edits and tool calls. This burns more tokens and grows the context. The other options are a person stepping in to redirect it or restarting the whole run from step one. That's wasteful, because it pays for every model/tool call again and re-prefills the context. Moreover, since an agent's run is non-deterministic, it doesn't reproduce the same early steps anyway. The reason it's hard to just jump back exactly to a previous correct step and resume from there is that the trajectory is only a message log. It records what the agent said and which tools it called, but not the live state underneath. That state includes things like memory, open file handles, child processes, installed packages, /tmp, and KV cache. None of that is in the log. Git can version the files, but it doesn't snapshot the running process or the KV cache. Checking out step eight moves the files back, but the process is still sitting in step-ten memory with a cold cache. Shepherd is a runtime layer by Stanford that records the run as a trace of typed events rather than a flat log. Each agent-environment interaction becomes a commit, similar to Git, but it tracks the live run. Its commit includes the agent process and the filesystem together, copy-on-write, so a branch carries the actual state and not just the files. Going back to a previous step is then a single call that forks from that commit and continues from the exact state. The copy-on-write fork is roughly five times faster than docker commit, and because the prompt prefix through step eight is unchanged, the KV cache is reused over 95% on replay, so early steps aren't reprocessed again. Once the run can be forked, a meta-agent can sit on top and operate it. It watches the trace and reverts as soon as it looks wrong, before the bad write is committed. In practice, it's just Python calling fork, replay, and revert on the trace, rather than a separate control plane wired into the harness. Not everything is reversible though. Files and sandbox changes undo themselves, but a database write has no automatic undo, so it needs a matching undo step set up in advance. Something external, like a sent email or a real charge, can't be undone, so the supervisor's job there is to catch it before it fires. They tested this on a few public benchmarks. On CooperBench, where two agents work on the same codebase, adding a live supervisor took the pair-coding pass rate from 28.8% to 54.7%. It's still early and labeled alpha. The benefit mostly shows up when a run gets branched a lot over a heavy sandbox state, which is exactly where restarting wastes the most tokens and time. If Git was made to make file changes reversible, Shepherd is trying to do the same thing for a live agent run. Shepherd Repo: (don't forget to star it ⭐ ) That said, Shepherd reverts a bad step inside a run. The harness around it, the prompts, tools, and checks the supervisor relies on, still drifts across runs as models and dependencies change. Akshay wrote about making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it can't recur. Read it below.

Avi Chawla

440,053 次观看 • 1 个月前

one of my favorite ways to use claude code skills right now - combining remotion with claude-in-chrome for motion video creation. the workflow is addictive. the clip you see here was produced with minimal prompting effort let me know if you would like me to write a full break down of this process. you describe to claude code what you want, claude code writes the remotion components, opens the remotion studio (via browser) with claude-in-chrome, sees the actual rendered output, and iterates on it in real time. need the arrows pointing to the center of the bubbles instead of the edge? just say it. need the layout shifted to the center? say it. claude sees the preview, adjusts the code, re-renders. then when you're happy you tell claude code to render the final video. but skills are what make this possible. remotion knowledge + browser automation + the taste to iterate visually. no copy pasting screenshots back and forth. no "can you try moving it 10px to the right" over chat. it just looks and fixes. this is the kind of workflow that makes you realize how much further claude code can go beyond just writing code in a terminal. i didn't touch any code while working on the clip you see if you haven't tried combining skills together like this - start experimenting. the skills combos is where the magic is at.
0:16

one of my favorite ways to use claude code skills right now - combining remotion with claude-in-chrome for motion video creation. the workflow is addictive. the clip you see here was produced with minimal prompting effort let me know if you would like me to write a full break down of this process. you describe to claude code what you want, claude code writes the remotion components, opens the remotion studio (via browser) with claude-in-chrome, sees the actual rendered output, and iterates on it in real time. need the arrows pointing to the center of the bubbles instead of the edge? just say it. need the layout shifted to the center? say it. claude sees the preview, adjusts the code, re-renders. then when you're happy you tell claude code to render the final video. but skills are what make this possible. remotion knowledge + browser automation + the taste to iterate visually. no copy pasting screenshots back and forth. no "can you try moving it 10px to the right" over chat. it just looks and fixes. this is the kind of workflow that makes you realize how much further claude code can go beyond just writing code in a terminal. i didn't touch any code while working on the clip you see if you haven't tried combining skills together like this - start experimenting. the skills combos is where the magic is at.

elvis

46,485 次观看 • 5 个月前

Usually when I save a website URL it's because -I want to save the website design exactly how it is in that point in time -I want to know what frontend/animation trickery they did whether its just raw code or some framework so i made a site where I just drop the url -> get a screenshot + screen recording to capture any animations I found interesting a non-trivial amount of my notion links don't resonate with me due to redesigns and I think this is the simplest fix. Just like my notion list it lives in a browser tab and is still paste->enter->move on
0:16

Usually when I save a website URL it's because -I want to save the website design exactly how it is in that point in time -I want to know what frontend/animation trickery they did whether its just raw code or some framework so i made a site where I just drop the url -> get a screenshot + screen recording to capture any animations I found interesting a non-trivial amount of my notion links don't resonate with me due to redesigns and I think this is the simplest fix. Just like my notion list it lives in a browser tab and is still paste->enter->move on

Sabina

38,649 次观看 • 4 个月前

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.
0:14

OpenClaw, but built for normal people. Sim is an open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.

Akshay 🚀

52,426 次观看 • 5 个月前

It's been several months since I curbed my phone addiction and it is so profoundly noticeable that my happiness has dramatically increased. I completely dropped doom scrolling, the news, politics, brain rot, and limit social media to mine and my friends' posts only. All the general negativity on the internet is like living in a home where everyone argues and is upset, even if it doesn't involve you and you don't engage with it, just being exposed to it every day is mentally draining. It's subtle, it creeps up slowly, and you don't even realize how mentally taxing it truly is. Now imagine the feeling of living in a home where everyone is peaceful and laughs, the feeling is equally infectious. You can even test this out by watching Friends or The Big Bang Theory with and without the laugh track on YouTube; spoiler, it's painfully cringe without it. The effect surrounding vibes have on your emotions is so strong, and it's hard to notice most of the time. I now find myself having uncontrollable fits of laughter at least once a week, which used to be closer to once a year. It's important to note that the things triggering these fits of laughing were always there, the difference is that my perception has changed. It's figuratively like a laugh track is playing in the background and all of a sudden, everything is now funny. I'm not trying to preach and tell people how to live their lives, but it's something I felt compelled to share since it's helped me so much. The habit was hard to break because the algorithm is designed to adapt to every person and lock you in, but I did it by substituting the phone with other things I enjoy. Right now it's learning the guitar and swimming. I'm developing skills I've never had, and it only compounds the feeling of happiness.
0:11

It's been several months since I curbed my phone addiction and it is so profoundly noticeable that my happiness has dramatically increased. I completely dropped doom scrolling, the news, politics, brain rot, and limit social media to mine and my friends' posts only. All the general negativity on the internet is like living in a home where everyone argues and is upset, even if it doesn't involve you and you don't engage with it, just being exposed to it every day is mentally draining. It's subtle, it creeps up slowly, and you don't even realize how mentally taxing it truly is. Now imagine the feeling of living in a home where everyone is peaceful and laughs, the feeling is equally infectious. You can even test this out by watching Friends or The Big Bang Theory with and without the laugh track on YouTube; spoiler, it's painfully cringe without it. The effect surrounding vibes have on your emotions is so strong, and it's hard to notice most of the time. I now find myself having uncontrollable fits of laughter at least once a week, which used to be closer to once a year. It's important to note that the things triggering these fits of laughing were always there, the difference is that my perception has changed. It's figuratively like a laugh track is playing in the background and all of a sudden, everything is now funny. I'm not trying to preach and tell people how to live their lives, but it's something I felt compelled to share since it's helped me so much. The habit was hard to break because the algorithm is designed to adapt to every person and lock you in, but I did it by substituting the phone with other things I enjoy. Right now it's learning the guitar and swimming. I'm developing skills I've never had, and it only compounds the feeling of happiness.

Macie Jay

74,206 次观看 • 1 年前

OK, I have a definitive word on the CJ Abrams play from today's Pittsburgh Pirates at Washington Nationals game after talking with Elias Sports Bureau on this. This play will stay as a sacrifice fly. The originial ruling of NOT a sacrifice fly was for the exact same reason that I thought, which is that the infielder is not running into the outfield, which is year's past would have been correct As it was explained to me, in past years, an infielder had to be running almost in a straight line towards the outfield wall to be considered "running in the outfield". Here, since he is running, and he ends up further away from home (157 feet) than when he started (145 feet), this is going to count as a sacrifice fly. That definition is changing, in part from this play to help bring greater consistency, and to take some of the guesswork out of it (the argument that he is running into the outfield as opposed to more parallel). Now, folks all the time ask "why doesn't MLB publish the OS Manual" and I always say because it is a living document that can have the wording change, and the wording for this play will be modified to something like "more towards the outfield wall than towards home plate" to eliminate any confusion. The big key to this play is that he was running on a full sprint. Also, and this is helpful for me, but for all fly ball outs that score a run, Elias Saba reviews to ensure consistency. So, yes, it's a sacrifice fly, and now that I have that info from Elias themselves, that sort of settles this one. Sounds like the guidelines for this definition will be changing, either this season, or certainly for next season.
0:14

OK, I have a definitive word on the CJ Abrams play from today's Pittsburgh Pirates at Washington Nationals game after talking with Elias Sports Bureau on this. This play will stay as a sacrifice fly. The originial ruling of NOT a sacrifice fly was for the exact same reason that I thought, which is that the infielder is not running into the outfield, which is year's past would have been correct As it was explained to me, in past years, an infielder had to be running almost in a straight line towards the outfield wall to be considered "running in the outfield". Here, since he is running, and he ends up further away from home (157 feet) than when he started (145 feet), this is going to count as a sacrifice fly. That definition is changing, in part from this play to help bring greater consistency, and to take some of the guesswork out of it (the argument that he is running into the outfield as opposed to more parallel). Now, folks all the time ask "why doesn't MLB publish the OS Manual" and I always say because it is a living document that can have the wording change, and the wording for this play will be modified to something like "more towards the outfield wall than towards home plate" to eliminate any confusion. The big key to this play is that he was running on a full sprint. Also, and this is helpful for me, but for all fly ball outs that score a run, Elias Saba reviews to ensure consistency. So, yes, it's a sacrifice fly, and now that I have that info from Elias themselves, that sort of settles this one. Sounds like the guidelines for this definition will be changing, either this season, or certainly for next season.

MLB Scoring Changes

49,141 次观看 • 1 个月前