|
|
|
|
|
|
by jampa
4 hours ago
|
|
|
From what you said: Not looking at code is bad, not because Claude can slip a few bugs (it can), but because LLMs tend to default to writing more code and features than needed, which isn't a good thing. I see a lot of people making 10+ PRs per day, but most of them are just going back to fix earlier PRs. Claude always likes to "go big," for example, by choosing tools that can support millions of concurrent users or by adding unnecessary layers of abstraction that create more maintenance pain. I guess that's good for LLM companies, since more tokens are spent fixing the mess it caused. Every time I enter plan mode for a huge feature, I end up cutting about 30-60% of the task scope before the LLM can actually start the work. I review the final code, and I still find things to cut. As said before "The best code is no code, or code you don’t have to maintain" [0] 0: https://www.simplethread.com/20-things-ive-learned-in-my-20-... |
|
|