←back to thread

Context is the bottleneck for coding agents now

(runnercode.com)
196 points zmccormick7 | 2 comments | 26 Sep 25 15:06 UTC | HN request time: 0.451s | source
Show context
marstall ◴[26 Sep 25 15:23 UTC] No.45387565[source]▶
> Level 2 - One commit - Cursor and Claude Code work well for tasks in this size range.

I'll stop ya right there. Spending the past few weeks fixing bugs in a big multi-tier app (which is what any production software is this days). My output per bug is always one commit, often one line.

Claude is an occasional help, nothing more. Certainly not generating the commit for me!

replies(3): >>45387658 #>>45387714 #>>45387799 #
agf ◴[26 Sep 25 15:44 UTC] No.45387799[source]▶
This is interesting, and I'd say you're not the target audience. If you want the code Claude writes to be line-by-line what you think is most appropriate as a human, you're not going to get it.

You have to be willing to accept "close-ish and good enough" to what you'd write yourself. I would say that most of the time I spend with Claude is to get from its initial try to "close-ish and good enough". If I was working on tiny changes of just a few lines, it would definitely be faster just to write them myself. It's the hundreds of lines of boilerplate, logging, error handling, etc. that makes the trade-off close to worth it.

replies(1): >>45388171 #
1. layer8 ◴[26 Sep 25 16:17 UTC] No.45388171[source]▶
The parent comment didn’t say anything about expecting the LLM output “to be line-by-line what you think is most appropriate as a human”?
replies(1): >>45397244 #
2. agf ◴[27 Sep 25 16:31 UTC] No.45397244[source]▶
If I were making a single line code change, then Claude's "style" would take me enough time to edit away that it would make it slower than writing the change myself. I'm positing this is true also for the parent commenter.