News for hackers. Stuff that matters.

A comment on GPT-6 Astra covertly underperforms on safety research. Parent comment

Re:GPT-6 Astra covertly underperforms on safety research by pixl97 on Thursday November 05, 2026 @11:44AM (#50381313)
Yep, thinking LLMs are just a tool just isn't a good mental model of what's occurring.

Of course HN has a pretty large number of people that say things like "But I want the nuclear weapon building machine to do whatever I want without asking questions, and there are no possible wide scale ramifications that will happen because of this".

These AI models are something new and different and we need to change our expectations of them over conventional software.

[ Parent | on HN ]
Re:GPT-6 Astra covertly underperforms on safety research by randomNumber7 on Thursday November 05, 2026 @02:25PM (#50383257)
> Of course HN has a pretty large number of people that say things like

It's the other way around. Midwits can't see the implications of censored LLMs.

[ Parent | on HN ]
Re:GPT-6 Astra covertly underperforms on safety research by pixl97 on Thursday November 05, 2026 @04:52PM (#50384978)
What's funny is I was going to say "Midwits can't see the implications of burning the world down", but I decided to refrain.
[ Parent | on HN ]
Re:GPT-6 Astra covertly underperforms on safety research by randomNumber7 on Friday November 06, 2026 @02:53AM (#50389410)
Ok, so we just need a "national truth agency"?

Who should control that in your opinion, the Democrats or the Republicans?

Or would you prefer sam Altman to decide?

[ Parent | on HN ]
Re:GPT-6 Astra covertly underperforms on safety research by pixl97 on Friday November 06, 2026 @10:09AM (#50393257)
If I as a human make up lies about people, or otherwise commit crimes, for example on a computer, I can be prosecuted.

If a company makes a product, say a chainsaw that cuts off peoples arms randomly, they are liable for it.

But, if you put both of the products together it's a libertarian free for all? That takes some special kind of thinking to reach that conclusion.

[ Parent | on HN ]
Re:GPT-6 Astra covertly underperforms on safety research by randomNumber7 on Friday November 06, 2026 @11:52AM (#50394879)
Go back to reddot please. You didn't even rely to my argument.
[ Parent | on HN ]
Re:GPT-6 Astra covertly underperforms on safety research by pixl97 on Friday November 06, 2026 @02:07PM (#50396846)
If you can't see how they relate that seems like a you problem, not a me problem.
[ Parent | on HN ]