Carlos

Here is the full talk:

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!

Excited to introduce RSI-Anything! One RSI model that works across coding, GUI, planning, or even Science tasks. Let's RSI Everything! 📄 Paper: arxiv.org/abs/2610.13912 💻 Code: github.com/Gen-Verse/RSI-Any… #RSI #WorldModels #RSI #AIAgents #AIforScience #JEPA

ChatGPT launched their version of Generative UI yesterday. We took it apart tldr; the agent never write raw code. It emits DIL (a new language), the server compiles and streams it, the client renders it using a component set so that it feels native

The terms for this sucks, and you agree to them by just applying. - §2.4 Anthropic "may develop similar or competitive technology" - §2.4 permits reuse, for any purpose, of general ideas, know-how and techniques remembered by personnel looking at your data - §D.4 prohibits accessing their services to build competing products or services - §F.1 allows them to retain and perform safety reviews, superseding ZDR (whats the point of ZDR then?) and it could get worse later! - §6 permits changes to the addendum at any time without notice or liability @jason you advising your start ups to apply for this? [1] anthropic.com/startup-progra… [2] anthropic.com/legal/startup-…

ok it's official... AI-written unit tests and integration tests are empirically proven to be unhelpful. you should tell your agents to stop writing tests by themselves on the deepswe eval set, banning sonnet 5.5 high from writing any tests actually resulted in slightly higher success rate (non stat-sig), with less time and token spent (stat-sig). this is pretty hard empirical evidence across the tests that were written by the "tests allowed" baseline arm, 65% of them were unit tests, 35% were integration tests, neither bucket resulted in any improvement compared to not writing any tests at all i also picked a random sample of 44 tasks subset where i completely disabled executing even existing tests - it also did not affect success rate at all i spot checked many tests written in the baseline arm, and my intuition is that most tests are simply a repetition of the implementation agent-written tests do not add any value because both the implementation and the tests were simply the agent's interpretation of our intent. the tests aren't any more accurate than the implementation itself i suspect we can still extract some value from unit tests and integration tests if we describe them ourselves when we believe we can articulate our intent better through test cases than through requirements. but i have not proven this yet also worth noting, during deepswe eval the agent wrote almost no e2e tests (only 17, compared to 3000+ unit/integration tests written). so this analysis does not prove nor disprove the value of e2e tests - i will do another eval specifically for that

Test-Driven Development (TDD) has been my default programming mode for 25 years. TDD simply made me a better developer. It’s been invaluable. However, the time has come to bid farewell. TDD didn’t survive my transition into AI-native development: forcing an agent through increments optimized for human cognition negates many of the benefits. Dropping TDD feels like a drastic step. But it’s similar to what happened years earlier as I went all in on Clojure. I had to adapt my habits and workflows to a new context in order to take advantage of it. My new essay reflects on my decades as a TDD practitioner, as well as the agentic characteristics that made me abandon the technique. adamtornhill.substack.com/p/…

We deleted 800k lines of unit tests from the @sazabi monorepo earlier this week. Three hypotheses: 1- Unit tests "lock-in" slop code by making it hard to change or remove 2- Unit tests slow down dev cycles by making your agent do more work locally and by increasing CI times 3- Unit tests waste money by making your agent generate more tokens and by adding useless CI runs Will report back soon with the results!

Introducing e2e The agentic testing framework for any app ~/ npx e2e init → Fully Open Source → Mix deterministic and agentic APIs → Supports web, mobile, and more → Bring your own agent and infrastructure → Run locally or in CI tester.army/e2e

OpenResearch was the #1 trending GitHub repo on Friday 🚀 With OpenResearch, you can turn any coding agent into a research agent that reviews literature, develops hypotheses, runs experiments, and produces research artifacts. Own and automate your research stack end-to-end. Now available on Windows. Check it out: github.com/alphaXiv/OpenRese…

Introducing Julia-1: Our first classification model that runs on almost anything. Learn more 👇 supersoniclabs.ia.br/julia-1…

How to use jev #1: As an embedder