←back to thread

Recent AI model progress feels mostly like bullshit

(www.lesswrong.com)
579 points paulpauper | 1 comments | 06 Apr 25 18:01 UTC | HN request time: 0s | source
Show context
joelthelion ◴[06 Apr 25 19:17 UTC] No.43604124[source]▶
I've used gemini 2.5 this weekend with aider and it was frighteningly good.

It probably depends a lot on what you are using them for, and in general, I think it's still too early to say exactly where LLMs will lead us.

replies(3): >>43604165 #>>43604223 #>>43609819 #
1. jchw ◴[06 Apr 25 19:23 UTC] No.43604165[source]▶
I think overall quality with Gemini 2.5 is not much better than Gemini 2 in my experience. Gemini 2 was already really good, but just like Claude 3.7, Gemini 2.5 goes some steps forward and some steps backwards. It sometimes generates some really verbose code even when you tell it to be succinct. I am pretty confident that if you evaluate 2.5 for a bit longer you'll come to the same conclusion eventually.