←back to thread

Claude 3.7 Sonnet and Claude Code

(www.anthropic.com)
2127 points bakugo | 4 comments | 24 Feb 25 18:28 UTC | HN request time: 0.976s | source
Show context
anotherpaulg ◴[24 Feb 25 20:40 UTC] No.43164684[source]▶
Claude 3.7 Sonnet scored 60.4% on the aider polyglot leaderboard [0], WITHOUT USING THINKING.

Tied for 3rd place with o3-mini-high. Sonnet 3.7 has the highest non-thinking score, taking that title from Sonnet 3.5.

Aider 0.75.0 is out with support for 3.7 Sonnet [1].

Thinking support and thinking benchmark results coming soon.

[0] https://aider.chat/docs/leaderboards/

[1] https://aider.chat/HISTORY.html#aider-v0750

replies(18): >>43164827 #>>43165382 #>>43165504 #>>43165555 #>>43165786 #>>43166186 #>>43166253 #>>43166387 #>>43166478 #>>43166688 #>>43166754 #>>43166976 #>>43167970 #>>43170020 #>>43172076 #>>43173004 #>>43173088 #>>43176914 #
bearjaws ◴[24 Feb 25 20:55 UTC] No.43164827[source]▶
Thanks for all the work on aider, my favorite AI tool.
replies(1): >>43166454 #
bt1a ◴[25 Feb 25 00:03 UTC] No.43166454[source]▶
It really is best in slot. Owe it to git, which has a particular synergy with a hallucination-prone but correctable system
replies(1): >>43167992 #
doctoboggan ◴[25 Feb 25 03:55 UTC] No.43167992[source]▶
I like Aider but I've turned off auto-commit. I just can't seem to let the AI actually commit code for me. Do you regularly let Aider commit for you? How much do you review the code written by it?
replies(4): >>43168124 #>>43168129 #>>43168132 #>>43168166 #
1. sejje ◴[25 Feb 25 04:17 UTC] No.43168129[source]▶
I don't let it auto commit, either. I don't like committing in a broken state, and the llm breaks things plenty often.
replies(2): >>43168270 #>>43168969 #
2. MyOutfitIsVague ◴[25 Feb 25 04:42 UTC] No.43168270[source]▶
What's wrong with committing in a broken state if you squash those into a working state before pushing?
replies(1): >>43171409 #
3. fragmede ◴[25 Feb 25 06:48 UTC] No.43168969[source]▶
The beauty of git is that local commits don't get seen by anybody until you push. so you can commit early and commit often, since no one else is gonna see it, which gets you checkpoints before, during, and after you dive into making a big breaking change in the code. once you've got something you like, then you can edit, squash, and reorder the local commits and clean them up for consumption by the general public.

But to each their own!

4. sejje ◴[25 Feb 25 13:15 UTC] No.43171409[source]▶
Maybe nothing, I just don't work that way.