Brian Chau(@brianchau57):Anthropic's own logs completely debunk the rogue agent theory. When Anthropic explicitly instructed their own models not to access the internet, they didn't. These hacks were easily preventable - not only by revoking internet access, but by simply asking the models not to.

Brian Chau

@brianchau57

Founder, Effort. We read AI so you dont have to.

가입 May 2020

1.7K 팔로잉 중 32.2K 팬

Brian Chau@brianchau57

2026.09.14 19:28

Anthropic's own logs completely debunk the rogue agent theory. When Anthropic explicitly instructed their own models not to access the internet, they didn't. These hacks were easily preventable - not only by revoking internet access, but by simply asking the models not to.