@Alezander9 in codex this is fork_turns="all" (the default) - forks also inherit the same cache key so it's cost efficient to do this. If your goal is to have an adversarial subagent observe an outcome without the history of the decision making process then fork_turns=None
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
@copyconstruct I’m finding that system one models (Jev, Decisions etc.) help pre-commit agent systems be more targeted. You can encode all your rules individually, run the diff through each gate and get the agents to work against the signal rather than a wide list of constraints
Great read & release 👏
In addition to the amazing open source repo, paper and learnings, AutoIllustrate is a super nice addition. Gonna give all this a spin and dig into the codex adapter 👀
The AI Scientist v3 is out: The Agentic Scientist.
GitHub: https://t.co/v2AkZi4Bmt
Blog: https://t.co/v3Td5yfvBE
arXiv: https://t.co/RuVnAHjMlK
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 https://t.co/i6fwB6vzQV 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!
Ohhh it’s out! The prediction quality is so good, it will usually describe the next best step in a little more detail than I would have and improves the overall outcome 🔥
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.
@matteing The most basic one is that I want to be able to move pages between spaces. If I start a page then I want to move it to a shared space, that should be a simple action 🙏