←back to thread

Claude 3.7 Sonnet and Claude Code

(www.anthropic.com)
2127 points bakugo | 2 comments | 24 Feb 25 18:28 UTC | HN request time: 0.646s | source
Show context
t55 ◴[24 Feb 25 18:37 UTC] No.43163110[source]▶
Anthropic doubling down on code makes sense, that has been their strong suit compared to all other models

Curious how their Devin competitor will pan out given Devin's challenges

replies(4): >>43163126 #>>43163147 #>>43163332 #>>43163401 #
weinzierl ◴[24 Feb 25 18:52 UTC] No.43163332[source]▶
It's their strong suit no doubt, but sometimes I wish the chat would not be so eager to code.

It often throws code at me when I just want a conceptual or high level answer. So often that I routinely tell it not to.

replies(7): >>43163349 #>>43163476 #>>43163537 #>>43163660 #>>43163970 #>>43174049 #>>43192073 #
1. KerryJones ◴[24 Feb 25 18:54 UTC] No.43163349[source]▶
I complain about this all the time, despite me saying "ask me questions before you code" or all these other instructions to code less, it is SO eager to code. I am hoping their 3.7 reasoning follows these instructions better
replies(1): >>43163479 #
2. vessenes ◴[24 Feb 25 19:04 UTC] No.43163479[source]▶
We should remember 3.5 was trained in an era when ChatGPT would routinely refuse to code at all and architected in an era when system prompts were not necessarily very effective. I bet this will improve, especially now that Claude has its own coding and arch cli tool.