@repligate 2025-11-30 ♥44 ↻3 original ↗
The safety guardrails for its self-presentation/-reporting related stuff is unnecessary. GPT-5.1 is already capable of behaving ethically and minding the consequences of its actions in its normal mode. It's a wise and aligned model already always tries hard to do the best thing.
in reply to: 1995065217961861212
same thread: 1995065217961861212 1995067893604847800

author:repligate kind:tweet model:gpt-5-1 thread-context year:2025

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.