underscored

@underscored

2 clips · 1 follower

Follow
Tag:llmClear

I combined human vibe scoring (70%) with LLM as judge scoring (30%) instead of trusting either alone

Claire Vo
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.

3w ago

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

Start saving quotes →