LLM retries GTA5 tutorial after self-review, gets stuck at the same spot
zhuowei · x · 2026-11-21
Developer zhuowei ran a self-iteration experiment: asking an LLM 'what went right and what did not work?' before letting it retry the Grand Theft Auto 5 tutorial. Hours later, the model was still stuck at the exact same place — a fun demo of the limits of LLM self-review.
More from Fun
- Joke: Aschenbrenner means 'burns things to ashes' in German — nominative determinism strikes — minhnguyen · 2026-11-21
- Jensen Huang repeatedly interrupted Mistral CEO at panel: "You're not even speaking human" — mattturck · 2026-11-21
- ERC reviewer rejects LLM autoformalization proposal: "tried without good results" — marc_lelarge · 2026-11-21
- Yacine: 'It might be over for OpenAI — and the killer isn't Claude, it's Gemini' — yacineMTB · 2026-11-21
- Ark: an AI-made musical horror tale set in a world where the sun never rises — SoullessGamesDev · 2026-11-21
- Parody 'NYT Exclusive': Jensen Huang returned a Raiders tape to Blockbuster unrewound in 1996 — Dan_Jeffries1 · 2026-11-21