voooooogel questions Mythos blog's simulation-reasoning logic and model reality training
voooooogel · x · 2026-09-11
Commenting on a blog post about model reasoning around being in a simulation, voooooogel raises two points:
- It's unclear what credence a model should have that it's in a simulation, especially when predicated on being told so — and it's an open question whether models are even trained to distinguish reality from simulations, or exposed to reality at all.
- He finds the Mythos blog post "kinda misleading": its reasoning doesn't actually flow from how realistic the scenario is, which is why edits didn't help.
A first-hand critique of simulation-scenario testing methodology for models.
More from Models
- 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
- xAI Rebrands as SpaceXSI, Launches Grok 4.7 and Unified Multimodal API — RachelVT42 · 2026-10-28