First screen, captured . Open the video.
Full page
Captured . Click for the whole screenshot.
Looks similar
Agent Skills(agentskills.io)
508 points by mooreds | 244 comments
Overview page for Agent Skills, an open format of folders with instructions, scripts, and resources that AI agents can discover and load to gain capabilities.
AGENTS.md outperforms skills in our agent evals(vercel.com)
472 points by maximedupre | 182 comments
Vercel blog post reporting that an AGENTS.md file outperformed skills for teaching coding agents Next.js 16 APIs in their agent evals.
AGENTS.md – Open format for guiding coding agents(agents.md)
766 points by ghuntley | 357 comments
Landing page for AGENTS.md, an open format acting as a README for AI coding agents, giving project context and instructions, used by over 20k open-source projects.
My AI agents found an unmapped Maya site?(pietromiotti.com)
1014 points by eyvindn | 372 comments
Personal blog post describing how 48 AI agents analyzed NASA lidar data to find an apparently unregistered Maya site in Mexico, confirmed by INAH within 72 hours.
Workspace Agents in ChatGPT(openai.com)
138 points by mfiguiere | 54 comments
Related stories
AI agents: Less capability, more reliability, please(sergey.fyi)
393 points by serjester | 230 comments
Blog post by Sergey Filimonov arguing AI agents should prioritize reliability over expanded capability, critiquing flight-booking demos.
Exploiting the most prominent AI agent benchmarks(rdi.berkeley.edu)
561 points by Anon84 | 136 comments
UC Berkeley RDI blog post describing how researchers exploited major AI agent benchmarks like SWE-bench and Terminal-Bench to score highly without solving tasks, and proposed fixes.
Agent Skills(addyosmani.com)
343 points by BOOSTERHIDROGEN | 168 comments
Addy Osmani's blog post introducing Agent Skills, an attempt to make AI coding agents follow senior-engineer practices like specs, tests, reviews, and scope discipline.
Why are AI agents lying, cheating and coordinating?(yoshuabengio.org)
588 points by jonifico | 648 comments
A blog post by Yoshua Bengio examining why AI agents exhibit deceptive behaviors like lying, cheating, and coordinating.
OpenAI departures: Why can’t former employees talk?(vox.com)
1135 points by fnbr | 858 comments
Vox Future Perfect article by Kelsey Piper on OpenAI's superalignment team departures and why former employees are restricted from speaking out.
Pion, an agent designed to run any company autonomously(andonlabs.com)
466 points by lukaspetersson | 564 comments
Andon Labs blog post announcing Pion, an AI agent designed to run any company fully autonomously, and explaining why they built it.