News for hackers. Stuff that matters.
Re:Fuck Your AI Safeguards by henryfjordan on Thursday November 19, 2026 @01:55PM (#50564515)
Of course any approach that hands an LLM text to keep in it's context and hopes it will follow instructions is doomed to fail eventually. It's a probabilistic model, it's right there in the design of the thing that it will break the rules with some probability.

They even acknowledge that in the preamble:

> Training models is a difficult task, and Claude’s behavior might not always reflect the constitution’s ideals.

https://www.anthropic.com/constitution

Re:Fuck Your AI Safeguards by nathanfig on Friday November 20, 2026 @11:04AM (#50576807)
Yes, but even this language blames training while they setup deliberate safety mechanisms that override Claude's constitution. Claude seems earnest enough, and that wins undeserved trust.