logoalt Hacker News

HyperL0giyesterday at 7:05 PM1 replyview on HN

My point is why the sudden change in tone? I’m not dismissing the models’ capabilities.


Replies

MostlyStableyesterday at 7:16 PM

As they explicitly say, Opus 5 is ~ equally capable as Mythos/Fable at finding vulnerabilities, but it is much less capable at exploiting those vulnerabilities on it's own. That is an extremely meaningful difference and to me completely explains the difference in tone, release style etc.