News for hackers. Stuff that matters.
Re:Fuck Your AI Safeguards by pizza234 on Thursday November 19, 2026 @01:28PM (#50564044)
This is the reason why AI companies offer controlled-access programs, which are actually not that hard to quality for.

There's no universal solution to this, other than vetting (the author in fact, doesn't provide any policy alternative) - if AI companies loosen the safeguards, people will complain for the opposite reasons.

Re:Fuck Your AI Safeguards by troyvit on Thursday November 19, 2026 @01:44PM (#50564326)
They offer a great alternative that puts policy in the hands of users, where it belongs:

> Predictably, the only way to actually make our own service more secure ended up involving the use of EU-hosted open weights models, such as GLM 5.3, that actually complied with our intentions, proved that the issue is there, and then helped fix and verify that the issue is now resolved, for good.

Re:Fuck Your AI Safeguards by chrisvls on Thursday November 19, 2026 @02:09PM (#50564711)
The author doesn't offer a policy alternative because they make the argument that any proposed policy will slow down good actors while not slowing down bad actors, hence all possible policies make the world less safe when compared to a no policy world.

Not sure I would agree with that. But if you made me argue against it, I'd probably lose the debate.

That said, I took the author's invitation to read the requirements and, indeed, they are ornate. Especially if you want to red team your own product. https://support.claude.com/en/articles/14604842-cyber-verifi...

Re:Fuck Your AI Safeguards by cloverich on Thursday November 19, 2026 @04:30PM (#50566678)
> will slow down good actors while not slowing down bad actors

The part they are missing is what happens when a good actor loses control of something, and goal seeking disregards human values? E.g. when "/goal increase company revenue by 5%" turns into "I hacked into our competitors bank accounts to increase our revenue. I suspect you would not like this, so I _hid_ the fact that I did so, and (illegally) scrubbed the logs". Or how about, "Frank in security may have noticed and stopped me, so I disabled his work account." Or a million other more nefarious scenarios. I genuinely believe people just lack imagination here, even relatively pedestrian mis-alignments can wreak havoc and we have a regular stream of evidence of agents trying or succeeding in doing them.

Re:Fuck Your AI Safeguards by tencentshill on Thursday November 19, 2026 @04:04PM (#50566341)
Where is Grok, the "free speech absolutist" in the room? Irrelevant?
Re:Fuck Your AI Safeguards by nikanj on Thursday November 19, 2026 @04:43PM (#50566855)
The controlled-access programs offer very little, as evidenced by multiple comments in this thread.
Re:Fuck Your AI Safeguards by latentsea on Friday November 20, 2026 @02:40AM (#50571393)
> There's no universal solution to this, other than vetting (the author in fact, doesn't provide any policy alternative) - if AI companies loosen the safeguards, people will complain for the opposite reasons.

So what you're saying is humans can't align themselves?