Hacker News Reader

Comment by smashed | Hacker News Reader

I must have missed something but can't you just prompt it to answer in your desired style? What am I missing here.

Commenting because I am struggling with this too, claude code seems to be so verbose no matter how I prompt it.

You can prompt it, and it almost immediately forgets. Or context compaxtion purges ut. Or it somewhat communicates with you in it, but writes all comments and docs in its original bloated style.

Training supersedes random markdown files and prompts

No, training tends to override system prompts at lot of the time.

Let's say Claude Code's system prompt is updated to recommend responding in Simplified Technical English. It'll work for the current generation of models. But Anthropic will train the next generation via RL on Claude Code traces as they do today. As long as they don't change their reward design, the next generation is going to be pulled towards Claudish again, because speaking Claudish gives higher rewards, so in the end the prompt doesn't really matter.

Ideally these things shouldn't work like this but this seems to be the sorry state of RL right now.

You miss that it is not just your prompt but also the various system prompts, plus how the model was trained. But you can reduce the verbosity (also with a setting in /config).

And memory and code comment styles - i think that’s a big one people forget about. You can prompt it all you want, when it sees elaborate comments in memory and code it will follow the style

But you can prompt it to reduce the verbocity of the comments as a project in itself - I will probably try Fable 5.1 for this.

Training is far more important than user prompts

Reply on news.ycombinator.com