Re:GPT-6 Astra covertly underperforms on safety research
by ahtihn on Thursday November 05, 2026 @01:26PM
(#50382557)
It very obviously is a strict computer program. It's a program executed by a computer, what else could it be?
Re:GPT-6 Astra covertly underperforms on safety research
by Dylan16807 on Thursday November 05, 2026 @02:06PM
(#50383030)
It's a blob of data where only 1% of it was written with intent and the behavior of mimicking text has to be wrangled and coaxed far more than with a normal program.
That's the rough intent of putting the word "strict" into that sentence.
Re:GPT-6 Astra covertly underperforms on safety research
by robrorcroptrer on Thursday November 05, 2026 @05:33PM
(#50385460)
What is the difference to meat brains?
Re:GPT-6 Astra covertly underperforms on safety research
by jack_pp on Thursday November 05, 2026 @10:33PM
(#50387832)
I mean you can try to threaten ssh with it's kids lives but I doubt it'll let you log in.
Re:GPT-6 Astra covertly underperforms on safety research
by thelaxiankey on Friday November 06, 2026 @12:13AM
(#50388476)
I mean besides the fact that it's, by construction, pseudorandom?
Would it make you feel better if the user said 'It'll make significant changes to how the code works. In the COT, it brings up explanations that resemble anxiety about copying code, and my suspicion is that this is the proximal cause of the changes it's making.' -- this is inarguably true, and very likely what the guy you're responding to meant.