PyTorch is heading to @NVIDIA #GTC26 in San Jose next week! 📍 Visit us at Booth #338 for: ✨ Helion kernel authoring demos ✨ ExecuTorch on-device inference ✨ Meet PyTorch core maintainers & experts Plus talks, hands-on labs & a hackathon! 🔗 https://t.co/Hn2DEgXXa5 https://t.co/YUK6iWvX3V

Perplexity Computer replaced $225K/yr in marketing tools in a single weekend. We built an AI marketing agent that scans hourly, manages budgets, detects fatigue, and coordinates several campaigns end to end. In one test run, it made 224 micro-optimizations to our ad stack. https://t.co/B0ueikpQyp

SHOCKING: Among Republican men under 50, 54% deny the Holocaust. We are so screwed. https://t.co/vt6ZmGsCoY

SHOCKING: Among Republican men under 50, 54% deny the Holocaust. We are so screwed. https://t.co/vt6ZmGsCoY

No way, a product that sucks doesn’t work as expected! https://t.co/zSVKcLk7uT https://t.co/aPzF2tlNm1

LabOS today goes into LabClaw🦞 Today we embedded Stanford LabOS AI-XR co-scientist into LabClaw with OpenClaw🦞 — turning it into the unified skill layer for biomedical AI agents and world model. No more separate systems. One install. Full Wet-lab + Dry-lab execution with XR. https://t.co/CydO4zbQyk #LabClaw #Claw #LabOS #OpenClaw #AIforScience 🦞 #Stanford #Princeton

@HamelHusain Hey I've got something for you that I haven't talked about publicly (yet): https://t.co/ctFk6dUOBZ + https://t.co/zIHnERcyRK

@HamelHusain Hey I've got something for you that I haven't talked about publicly (yet): https://t.co/ctFk6dUOBZ + https://t.co/zIHnERcyRK

The @figma MCP server now supports a full roundtrip workflow from @code! Bring Figma designs into code, then capture your rendered UI back to the Figma canvas as editable frames. Join us for a special livestream tomorrow at 9:30 am PT to see it live in action: https://t.co/U1GFnSjUGV

@figma Learn more about how the Figma MCP server can now generate design layers from VS Code: https://t.co/3iVYA7Qtsf

introducing @Opnmatter — an infrastructure company for real-world agents. today, agents can write code, manage emails and work with money. but they can’t execute on real world actions due to the lack of addressable rails. we’re changing that. 1/5 https://t.co/yodYCfnT6m https://t.co/krMXD8apIo

Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs. https://t.co/AL2J4efxPw

Rosy-faced Lovebirds on Saguaro cactus 🌵 https://t.co/hIrjuaFbfp

Rosy-faced Lovebirds on Saguaro cactus 🌵 https://t.co/hIrjuaFbfp

A shepherd in abandoned Sacred Grove, Italy, ca. 1952 - by Herbert List (1903 – 1975), German https://t.co/O6DXE1EXAg

A shepherd in abandoned Sacred Grove, Italy, ca. 1952 - by Herbert List (1903 – 1975), German https://t.co/O6DXE1EXAg

scrolling through this site feels like watching a movie → https://t.co/a41OXXNDFB https://t.co/jvN7Z1LVvM

"If Trump can depose any leader he likes, what is to stop Russia or China acting similarly against their foes? (Russia, of course, already has tried, in its war on Ukraine.) Is that the world we want to live in?" https://t.co/lvjGKwuJmv

today we're launching struct - the on-call agent every team deserves. and we're making it free. no sales call. 5 min setup. 80% faster on-call. https://t.co/vuX7iATL2l

Super excited to present MetaClaw 🦞 — our self-evolving agent that learns just by talking to it. 💬 Conversations → training trajectories 🧠 Failures → new reusable skills ⚡ Weights update live (no interruption) ☁️ Powered 100% via API — no GPU cluster needed Try it here 👇 https://t.co/p5yqdWmwzR Huge kudos to the team @richardxp888, Jianwen Chen, @Xinyu2ML, @lillianwei423, @StephenQS0710, Zeyu Zheng, @HuaxiuYaoML

@Yuchenj_UW Codex is a know issue :( It basically don't work with autoresearch sadly, in the way it's set up atm: https://t.co/4xjdf4wQyX I pung a friend at OpenAI to see if something can be done, e.g. need a /loop equivalent or something like that. More generally, I really dislike the -p + ralph loop pattern of running agents "headless". I want nice, interactive sessions running in tmux so that I can see what they are doing, pitch in, etc.

Andrew Ng just solved one of the biggest problem with Agents. He released Context Hub, a CLI tool to fetch live API documentation. One command. The agent gets exactly what it needs before writing a single line of code. Agents trained months ago are flying blind. They invent parameter names. They call functions that no longer exist. They confidently write code against a spec that changed in the last release. > No more hallucinated parameters > Docs pulled fresh before each call > Agents log useful discoveries > Notes persist between sessions The agent runs a CLI command before touching the code. Instead of relying on stale data, it reads the actual spec. Fast-moving APIs used to mean maintaining a doc dump in every prompt. Now the agent does that work itself. When it finds a workaround, it saves a note for next time.

https://t.co/e7xglk9wXC

🚨 New: Integrating Harbor (@harborframework) for end-to-end Computer-Use evaluation(for Windows and Linux) at scale with @thinkymachines' Tinker, OSWorld, @daytonaio, and bare-metal servers. We just added support for Computer Use, @tinkerapi, and OSWorld to Harbor - a framework for evaluating agents and generating RL training data by running large-scale rollouts across parallel sandboxed environments and collecting trajectories for SFT and RL. Repo and blogpost below 👇