RSI Arena: 8 research agents autonomously train rival models for human judging
my_cat_can_code · x · 2026-09-30
LIVE RSI Arena, run with Stanford, Notre Dame, UW and Scale AI, tests how much post-training research frontier models can do autonomously: 8 research agents start from the same 30B base model, sharing 64 RTX PRO 6000 Blackwell GPUs for 144 hours (1,000 GPU-hours each), choosing their own data and writing training code. A final human evaluation decides whose trained model wins.
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