←back to thread

Coding with LLMs in the summer of 2025 – an update

(antirez.com)
600 points antirez | 1 comments | 20 Jul 25 11:04 UTC | HN request time: 0s | source
Show context
Keyframe ◴[20 Jul 25 13:55 UTC] No.44625227[source]▶
Unlike OP, from my still limited but intense month or so diving into this topic so far, I had better luck with Gemini 2.5 PRO and Opus 4 on more abstract level like architecture etc. and then dealing input to Sonnet for coding. I found 2.5 PRO, and to a lesser degree Opus, were hit or miss; A lot of instances of them circling around the issue and correcting itself when coding (Gemini especially so), whereas Sonnet would cut to the chase, but needed explicit take on it to be efficient.
replies(3): >>44625543 #>>44626481 #>>44629413 #
1. antirez ◴[20 Jul 25 16:02 UTC] No.44626481[source]▶
Totally possible. In general I believe that while more powerful in their best outputs, Sonnet/Opus 4 are in other ways (alignment / consistency) a regression on Sonnet 3.5v2 (often called Sonnet 3.6), as Sonnet 3.7 was. Also models are complex objects, and sometimes in a given domain a given model that on paper is weaker will work better. And, on top of that: interactive use vs agent requires different reinforcement learning training that sometimes may not be towards an aligned target... So also using the model in one way or the other may change how good it is.