GPT-6.1 Sol users hit frequent false-positive refusals even on mundane coding tasks
CtrlAltDwayne · x · 2026-10-05
User CtrlAltDwayne complains that GPT-6.1 Sol's safety guardrails are overly aggressive: even routine work on a simple PHP app keeps triggering refusal messages, despite content unrelated to typically flagged categories like biology. The over-blocking makes the model frustratingly slow to use.
More from Models
- Google doesn't need the best model: a faster, cheaper Gemini Pro stays competitive — haider1 · 2026-10-05
- Claude asks user whether to pull an all-nighter or finish the task tomorrow — prasenx · 2026-10-05
- Pro plan users hit Claude weekly limits after ~7 full 5-hour sessions, community tally finds — ckonfy · 2026-10-05
- OpenAI's Decisions API announced at DevDay still has no pricing or docs a week later — Balance- · 2026-10-05
- Day 1 of OpenAI's '28 Days of Improvements': community guesses GPT-6.1 Sol arrives in ChatGPT — mark_k · 2026-10-05
- ChatGPT is adding picture ads, starting inside the image generation flow — ross2000 · 2026-10-05