Stanford, Scale AI and others to livestream research agents doing autonomous post-training at COLM 2026
my_cat_can_code · x · 2026-09-30
An experiment co-organized by Stanford, Notre Dame, UW, Scale AI and bakeaihq, debuting at COLM 2026 in San Francisco, will livestream research agents orchestrating agentic post-training with no expert in the loop.
Key questions: will the competing agents collaborate or race to grab and hoard GPUs? Which frontier model makes the best post-training researcher? Viewers get to weigh in.
The quoted author is especially curious about what happens after an experiment fails — whether agents can diagnose why, change direction, and use their remaining compute well, since knowing what to try next and when to stop is the core of research. Independent evaluation of these decisions should clarify where autonomous research stands.
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16