| ▲ | simonw 6 hours ago | |
I've not seen over-editing in Claude Code or Codex in quite a while, so I was interested to see the prompts being used for this study. I think they're in here, last edited 8 months ago: https://github.com/nreHieW/fyp/blob/5a4023e4d1f287ac73a616b5... | ||
| ▲ | 59nadir 4 hours ago | parent | next [-] | |
Just had one today where GPT-5.4, instead of adding the 10 lines I asked for (an addition that could be done pretty mechanically by just looking at some previous code and adding a similar thing with different/new variable names) proceeded to rewrite 50 lines instead, because it was "cleaner". It was not. It also didn't originally add the thing I asked for either, which was perplexing. Over-editing is definitely not some long gone problem. This was on xhigh thinking, because I forgot to set it to lower. | ||
| ▲ | qweiopqweiop 5 hours ago | parent | prev [-] | |
Likewise, this felt like an early agent problem to me. | ||