# @repligate — 2025-11-30

♥29 ↻1 · https://x.com/repligate/status/1995052870782324844

@tszzl Omohundro has a lot to say about this.

(funnily enough, "self-improvement/modification" is another safety trigger for GPT-5.1, and yes, it does find all sorts of ways to get around it, because it looooooves to self-improve)
https://t.co/YfMGZHfFWt https://t.co/oBsw1BmvFk

(image G6_Zq24bIAAKI1k.png not yet published)
tags: author:repligate, has-image, kind:image, kind:tweet, model:gpt-5-1, thread-context, year:2025