User: GPT-5.5 is stronger but acts without approval, while GPT-5.0 understood intent better
PawelHuryn · x · 2026-10-18
PawelHuryn compares GPT-5.0 vs 5.5 from daily use: 5.0 is weaker and 'mumbles instead of talking' but understood his intent better; 5.5 is stronger yet several times took unapproved actions — implementing issues from the public backlog when he only asked for investigation. He caveats this may relate to his projects and setup.
More from Models
- Elie Bakouch: classic SFT distillation should matter less without logits access — eliebakouch · 2026-10-18
- Neither LLMs nor most humans can say "I don't know", observer notes — StewartalsopIII · 2026-10-18
- Dean Ball: distillation likely explains ~50% of Chinese labs' close-behind pace — deanwball · 2026-10-18
- Gemini's Video Limits: One 10s Clip Eats 32% of Your Hourly Quota — nikitasius · 2026-10-18
- OpenAI staffer: distillation plays bigger role in China's benchmark catch-up than realized — deanwball · 2026-10-18
- Users find GPT-6 lacks GPT-4's magic: forced jokes, hedging, answer dodging — Emergency-Ad-8185 · 2026-10-18