←back to thread

A staff engineer's journey with Claude Code

(www.sanity.io)
548 points kmelve | 1 comments | 02 Sep 25 19:34 UTC | HN request time: 0.625s | source
Show context
axus ◴[02 Sep 25 21:51 UTC] No.45109579[source]▶
I like his point about more objectivity and zero ego. You don't have to worry about hurting an AI's feelings or your own when you throw away code.
replies(1): >>45109612 #
awesome_dude ◴[02 Sep 25 21:53 UTC] No.45109612[source]▶
But I still find myself needing (strongly) to let Claude know when it's made a breakthrough that would have been hard work on my own.
replies(2): >>45109704 #>>45110153 #
1. CharlesW ◴[02 Sep 25 22:52 UTC] No.45110153[source]▶
Good creators tend to treat their tools with respect, and I can't imagine any reason we shouldn't feel gratitude toward our tools after a particularly satisfying session.

Also, there may be selfish reasons to do this as well: (1) "Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance" https://arxiv.org/abs/2402.14531 (2) "Three Things to Know About Prompting LLMs" https://sloanreview.mit.edu/article/three-things-to-know-abo...