Re:GPT‑6 and Intelligent UI for everyone
by Razengan on Wednesday October 07, 2026 @09:40PM
(#50001023)
It's good that they mention that. Most of those "guardrails" were overeager and caught too many false positives, crippling the AI. Like how Claude 5.5 refuses to do shit if a prompt contains "reasoning" because it thinks you're trying to hack it etc.
[ Parent
| on HN ]
There are no comments on this comment yet.