Loading activity…
@james_y_zou
@Stanford professor. Chan-Zuckerberg @biohub investigator. Sloan Fellow. Overton Prize. @togethercompute. AI for science + health.
AI
sanjana__z calls cascade harnesses recent work; james_y_zou claims switching can improve performance while cutting cost and token use.
AI
A researcher says their lab is interested in what future AI agent collaboration will need to be useful and safe.
AI
A post introducing the approach says its two modes combine latent-space thinking with text-based actions in one multi-turn flow.
AI
A post introducing OSVerify says its one-sided verifiers filter flawed research while keeping human review manageable.
AI
A project researcher says introspective consistency helps diffusion language models match autoregressive quality while keeping fast parallel decoding.
AI
GXL says the two-day build will focus on agentic science and kick off JPM week.
AI
Together’s Auto router selects a model once per session; an optional Anthropic key changes the choices.
AI
A researcher announced Paper2Agent’s publication in Nature on September 16, describing it as a way to turn papers into “virtual authors” that can answer questions and apply their methods.
AI
A user called September 24 decision day for NeurIPS 2026 and wished people good luck.
AI
A post sharing a Science release says the clinical trial forecasts addressed both efficacy and avoiding side effects.
AI
Nature describes Paper2Agent as turning manuscripts, code and data into AI systems that can invoke tools.
AI
Stanford researchers model how LLM agents update opinions through statistical physics laws.
