1–10 of 29 posts
I've been using Claude 3.5 for a couple of days now and I must say this is insane. It is so much better than OpenAI at coding.
I am a Data / Backend guy and I don't have that much experience with React / JS browser frameworks. Claude is incredibly good in writing good code fast. I've been using ChartJS with some pretty esoteric plugins and Claude nails every question first try.
What is your experience with it, do you feel the same?
Tbh it's making a lot of mistakes when writing with the latest Next.js versions of the new modules.
Maybe because of the knowledge cutoff? Idk
(Or maybe it's a signal to stop coding in JavaScript...)
Also, Claude artifacts can display MermaidJS. You can give it a whole codebase and ask something like "generate a sequence diagram of this process" and it does a remarkable job of doing so, displaying results in realtime.
You can see examples of the prompts it generates in the repository linked below, including a customized version of their prompt generator[2]. This feature significantly improved my experience with LLMs in general, both Claude and local ones, and I now use Claude 3.5 Sonnet for pretty much all my coding, mostly in Go and, lately, Rust.
I mostly use it to improve existing code or to get started, not to generate entire code bases, so I can't say much about that.
I found it lacking in shell scripting though. Nine out of ten times I need to fix the shell script it generates, to a point where I just gave up trying and went back to writing them from scratch.
Can't wait to see how much better Claude 3.5 Opus is, though.
[1]: https://docs.anthropic.com/en/docs/build-with-claude/prompt-...