> A machine cannot "argue" with me, it doesn't want anything nor does it have beliefs or experiences.

Yup I thought that too when reading TFA but then...

It gets really tiring when you see it making glaringly obvious mistakes which you point out because you don't want it to keep making the same mistakes only to be met with an answer that begins with "The point is ...".

I'm not shitting you: Anthropic models shall happily begin a sentence with "The point is ...", when it's not the point and it's just wrong.

Now, to me it's not an issue in that I can change its tone (if anything I can ask another LLM to rewrite me not the code but the english sentences any model spouts out to something nicer) but it is an issue in that you lose time: you just want it to acknowledge its errors so that it stops doing them.

That this thing "argues" (even if we know it doesn't argue) is representative of the fact that it is wrong and refuses to "admit" it (by that I mean: do not consider it important and hence shall keep making the same kind of mistakes).

And that is a problem.

Once it's in this loop, Opus 4.8 digs in so aggressively it's structurally incapable of conceding a provided detail as correct, even if it's conceded and agreed with everything backing that detail. Like actually, structurally incapable. I've even baited it into arguing with itself when I've "conceded" its original concern tolling hard, and then the model needs to continue to be the "voice of reason" and it will argue against its original concern because I, the user, said it.