underscored

@underscored

5 clips · 1 follower

Follow
Tag:prompt-engineeringClear

Why under-prompting frontier models gets better results than detailed step-by-step instructions

Claire Vo
1w ago

The open chat field has been good enough, until it stopped being good enough. I acknowledge in this episode that just typing into Claude Code has produced real work. But this marks a shift in my thinking: general-purpose agents are now better used to orchestrate specialized harnesses than to do every job themselves. Giving a constrained agent a specific harness gets more consistent output than giving a powerful agent an open prompt.

2w ago

The model doesn't actually remember previous conversations unless you use the Memory feature or paste in prior context yourself. Each new chat window starts completely fresh, which means if you want consistency across sessions, you have to build that context manually.

1mo ago

Underscored — save the words that stop you in your tracks.

Start saving quotes →