Comment by jakozaur
9 hours ago
E.g., your prompt for simple auth works (e.g., decode JWT), but your sessions stop because you are flagged for cybersecurity risk.
The Fable is the worst offender, and it is not purely Anthropic's fault.
9 hours ago
E.g., your prompt for simple auth works (e.g., decode JWT), but your sessions stop because you are flagged for cybersecurity risk.
The Fable is the worst offender, and it is not purely Anthropic's fault.
It's happened to me exactly twice in about 6 months of using codex (via pi). Both times were completely bogus and annoying but still, it's not too bad.
OpenAI's models have a lot less false positives for me. Almost always smooth doing vuln scans and fixing them.
Anthropic, whether Opus 5.5 or Fable, frequently will review for security, and the classifiers fire mid-way while it's fixing something. Authentication and credential related code, including implementation, also trigger safeguards.
Earlier today, I hit what appears to be a sticky "reasoning_extraction" block when attempting to reproduce a LLM paper at small scale, and I asked it ~"tell me more about the idea [X] you considered but dropped". I'm not sure how it works or how long it lasts, but Opus 5.5 has refused to do technical LLM work for me now, even in completely new sessions.