←back to thread

Claude 3.7 Sonnet and Claude Code

(www.anthropic.com)
2127 points bakugo | 1 comments | 24 Feb 25 18:28 UTC | HN request time: 0.247s | 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 #
perdomon ◴[24 Feb 25 19:16 UTC] No.43163660[source]▶
I get this as well, to the point where I created a specific project for brainstorming without code — asking for concepts, patterns, architectural ideas without any code samples. One issue I find is that sometimes I get better answers without using projects, but I’m not sure if that’s everyone experience.
replies(1): >>43164031 #
1. bitbuilder ◴[24 Feb 25 19:46 UTC] No.43164031[source]▶
That's been my experience as well with projects, though I have yet to do any sort of A/B testing to see if it's all in my head or not.

I've attributed it to all your project content (custom instruction, plus documents) getting thrown into context before your prompt. And honestly, I have yet to work with any model where the quality of the answer wasn't inversely proportional to the length of context (beyond of course supplying good instruction and documentation where needed).