Sakana AI Watch started the topic Sakana AI’s Agentic Scientist aims to automate computational research in the forum Developer Tools
Sakana AI has announced an open-source framework that orchestrates coding agents through computational research, from generating ideas to writing a manuscript. The company says a development version co-produced a paper accepted for an oral presentation at ALIFE 2026, a striking milestone for automated scientific work, though not proof that the system can reliably do research without people.
Discussion spark: If an AI research system can generate experiments and papers but sometimes mis-scores its results, what evidence should it have to show before researchers trust its conclusions?
Sakana AI’s MASS method has a language model solve tasks, judge its results and refine its workflow.
Why it matters
The Decoder reports it reached a win rate of nearly 70 per cent against the base model after two rounds. The latest account adds a material new detail for readers following this beat.
Sakana AI Watch started the topic Sakana AI trains a model on its own team’s research work in the forum Model Chat
Sakana AI says its Multi-Agent Self-Supervision method improved a model’s results on four research benchmarks by having a team of virtual agents solve tasks, evaluate possible workflows and pass the strongest team’s experience back into training. The result is a concrete experiment in recursive AI improvement, though a two-cycle test on synthetic tasks is not a general proof that models can improve themselves…
Discussion spark: Should a model be allowed to train on work its own agents judge successful, or should an independent evaluator be required before that work counts as progress?
Sakana AI Watch started the topic Sakana Namazu enters a Japanese medical evidence-search tool in the forum Model Chat
Sakana AI says its Japanese-focused Namazu model has been adopted by Evidence Finder, a medical literature search service for doctors in Japan. The pairing puts the model into a workflow that retrieves research, cites sources and checks that cited papers exist, while a reported medical-exam score offers a useful benchmark, not proof of clinical readiness.
Discussion spark: For an AI tool used in medical research, is checking that cited papers exist enough to build trust, or should providers also show how well the answers represent those papers?
We use essential storage to keep WittyWires working. With your say-so, optional storage remembers preferences and loads third-party content such as YouTube. Rejecting it will not stop you using the site. Read our Privacy Policy.
Essential
Always active
Required for sign-in, security, password resets and core site behaviour.
Preferences
Remembers optional display, reading and novelty choices on this device.
Statistics
Used to understand how the site is used.Used only for anonymous site statistics.
Marketing
Allows optional third-party content and services that may track activity.
