Kayvane Shakerifar

Introducing Querio The first analytics platform that puts your entire data stack in a git repo you own Querio makes your agents 100% consistent on your data Comment 'data teams' and i'll send you our open-source repo to move your BI tool to a git repo you own

The AI Scientist v3 is out: The Agentic Scientist. GitHub: github.com/SakanaAI/AI-Scien… Blog: pub.sakana.ai/agentic-scient… arXiv: arxiv.org/abs/2610.18933 The Agentic Scientist is the 3rd iteration of our automated AI Scientist research system, and the shift this time is from “one agent writes a paper” to “a scaffold of parallel agents orchestrates the full research loop.” The system now orchestrates a pool of parallel workers that share memory and distilled conclusions. Crucially, it features Evidence Generation: isolated agents automatically run controlled baselines and ablations to prove why an idea actually works. It works as a co-scientist. We used a development version as a co-scientist to explore biologically plausible learning rules. The agent handled the empirical heavy lifting, proposing mechanisms and running experiments. We stayed in the loop to steer direction, verify results, and moderate claims. That feels like the right division of labor for where the technology actually is. This resulted in a new biologically plausible learning algorithm, and the resulting paper was accepted at ALIFE 2026 as an oral presentation. We are also releasing AutoIllustrate. It generates editable draw.io vector figures instead of uneditable, hallucinated raster images. Real scientists need vectors, not pixels. I am an SVG junkie ;) Incredible work by Robert Lange, Luca Grillotti, Yutaro Yamada, Rujikorn Charakorn, and the team!

Now in beta: composer predictions in Codex for Pro users. Codex can now suggest your next message based on your conversation and how you talk to it. One of the most loved new features we've ever tested internally.

There's a rumor going around that Anthropic solved Navier-Stokes using LK-99.

We closed 1,500 issues on 𝚟𝚎𝚛𝚌𝚎𝚕/𝚗𝚎𝚡𝚝.𝚓𝚜 in one month by building a 𝚌𝚕𝚘𝚜𝚊𝚋𝚒𝚕𝚒𝚝𝚢 agent with @eve. The workflow: 1. Search related work 2. Try to reproduce bugs across versions in a sandbox 3. Return context for review nextjs.org/blog/how-we-close…

My course to build ambitious, modern frontend interfaces with Codex is out ✨ Learn how Codex can help you build frontend applications, debug them, and deploy them through hands-on exercises - check it out on @MasterDotDev Crazy how much you can get done in a few hours now.

Basically: if it’s something you’d normally have to open a browser and click through yourself, try asking ChatGPT Work to do it. Logging into websites is rolling out today on web and mobile for Plus, Pro, and Business users.

every time you intervene and correct your agent, you should think about how to eliminate it entirely. in order of value: 1. categorically eliminate the problem through better architecture or choice of data structures 2. turn it into a lint rule or test so CI catches it 3. turn it into a skill or rule 4. have humans review the code to catch it (ngmi)

This went under the radar this week, but we just shipped the ability for models with multi agents v2 to delegate to any supported model, including Luna! Took a bit of time to make sure this worked reliably

Old news actually from a bunch of days ago, but crossed that 15M. Enjoy a nice reset everyone. Landing in the next hour or so, go /fast.

`@`visualize is so powerful for creating form-like prompt inputs it can be your own custom request_user_input tool