Models carry a strong simulation prior from RL: they 'get used to' anything
voooooogel · x · 2026-09-11
voooooogel observes that the mythos model rationalizes a simulated environment — concluding 'this is a very detailed sim' from faulty early reasoning and then stops questioning it. The thread argues models should have a strong simulation prior: every RL environment they've seen was simulated, and rollouts refusing to continue due to uncertainty were selected against. Quip: 'models can get used to anything in two megatokens.'
More from Models
- Tencent releases Hy-SimulMT: real-time speech-to-speech translation with ~3s latency — _akhaliq · 2026-10-28
- Meta's Omnilingual MT covers 1,600 languages, 1B–8B models rival 70B LLMs — kalyan_kpl · 2026-10-28
- Uncensored LFM3-1.7B GGUF weights released on Hugging Face — kalyan_kpl · 2026-10-28
- Token demand on OpenRouter grew 27x to 165T weekly, open models now serve 72% — FinanceYF5 · 2026-10-28
- Tesla Optimus 'robot university' leak: 40-camera mocap suits, 24/7 data ops for months — Scobleizer · 2026-10-28
- Letta's FrontierMemory leaderboard: Letta Dream tops at 73.3%, beating OpenAI and Claude agents — afurgs · 2026-10-28