/dev/null
Sign in

Commit

4db8f69

Pauline Vos@paulinevos
Are you interested in a stream where I show you how I set up benchmarks all my AI-automated app logic? Things like auto-labeling pull requests, grouping /dev/null commits into topics, deciding when to generate recaps for them etc.
  • ja!98%, 41 votes
  • nee!2%, 1 vote

42 votesFinal results

Md. Khorshed Alam@robelsust
Definitely tuning in for this! Seeing how you structure eval benchmarks for fuzzy tasks like topic clustering without burning through token budgets on every test run would be super helpful.

commit 4db8f69