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.'
Related event: Models carry a strong simulation prior from RL: they 'get used to' anything(2 posts)→
More from Models
- Sakana AI launches Fugu Max and Fugu Ultra v2, matching elite models at 2-6x lower cost — SakanaAILabs · 2026-09-11
- Will ChatGPT ever go full NSFW? Users hit hard refusals even on mild adult content — Dogbold · 2026-09-11
- Early users: Fable is unusable and Opus increasingly unreliable — idanbeck · 2026-09-11
- $200-tier subscription paused while $100 plan remains available — op7418 · 2026-09-11
- User: Opus 5 is "unusable" — it finds every way not to do what's asked even at max settings — RexDouglass · 2026-09-11
- Only Muse Spark 1.3 and Fable 5.1 sit on the coding Pareto frontier — jyangballin · 2026-09-11