Anyone out there that's got some expertise in doing AI prompt evaluation? 🤞🏼

I've been experimenting with a new prompting technique that's showing promising results, but really want to put its through its paces.

Co-founder XMTP, building web3's secure messaging layer ➡️ https://xmtp.org

Poet-lawyer serving up narrative counsel. Passionate about developing language frameworks empowering us all to win it all.

Both! Qualitatively the thing is doing well. But I want to test it with harder instructions and measure quantitatively.

yes ! do you mean quantitative or qualitative evaluation?

aichannel

try asking specifics in /aichannel 

broadly familiar with evals/benchmarks/rubrics if you’re wondering smthn specific

It depends on what AI you use. If you’re using cursor I can recommend checking out cursorrules 

It pre sets all prompts by giving cursor rules in advance

It depends on what AI you use. If you’re using cursor I can recommend checking out cursorrules 

It pre sets all prompts by giving cursor rules in advance 

https://www.cursorrules.org