[ulrikrasmussen]

Do you think this is inherent or an artifact of prompting? Curiosity and side quests leads to higher token usage and longer time to finish, so I could understand why current harnesses and system prompts would not encourage that sort of thing.

But what if a coding agent was prompted to be more curious during development? Like a human developer, make mental notes of alternatives to try out and chase suspicious looking code which may seem unrelated to the task at hand. It could even spawn rabbit hole agents in parallel.

Taking a step back, this probably highlights major hazard with the increased usage of LLMs for coding, which is that everyone's style of work is going to converge because most code will be written by the 2-3 most popular models using the same system prompts.

[timcobb]

> Do you think this is inherent or an artifact of prompting?

Not sure! I mean, look at this sibling comment for example: https://news.ycombinator.com/item?id=48062797. Not my experience, but apparently others have this experience.

> But what if a coding agent was prompted to be more curious during development?

I've tried using the language of curiosity. My qualitative take was that it did have a positive impact, but not much. And I can only tinker with system prompting so much, before I get drawn into LLM driving :)

> which is that everyone's style of work is going to converge

yeah I imagine even people's styles of thinking will converge as a result of this, more so than from reading other people's prose or programs. I think I saw something on HN to this effect within the last month, too.

[lloeki]

I've seen something similar, solutions generated feel very pythonic or javaesque in languages that are neither Python nor Java (C, Rust, Ruby)

I've had to explicitly direct the machine to read existing sibling code and follow the specific idioms and patterns in use.