logoalt Hacker News

drnick1 • today at 6:29 PM • 2 replies • view on HN

Recent Anthropic/OpenAI models are increasingly displaying warnings or outright refusing to perform rooting, hacking, and binary reverse engineering. At this pace, they will be completely useless soon at entire classes of tasks I have found them most useful for.


Replies

sunaookami • today at 6:44 PM

GLM is perfect for these kind of things. GPT and Claude shit themselves even on stuff for very old devices that are no longer sold, nor "normally" usable.

➕ show 2 replies
oilkillsbirds • today at 6:40 PM

Good.