News for hackers. Stuff that matters.
Re:GPT-6 Astra covertly underperforms on safety research by sobellian on Thursday November 05, 2026 @04:45PM (#50384881)
I ran into (2) when trying out nanoclaw many months ago (turned out to be useless, I ditched it). I wanted an LLM to sort my email like an EA might, what I got was an LLM writing regexes to attempt to sort my email. If LLMs have been trained to be the ultimate programmers, the one pitfall is that the best programmers tend to be lazy.

There are no comments on this comment yet.