Evals Office Hours

Saturday, October 3
12:00 – 1:00 PM
Online event
The join link is shared with registered guests
Registration

Welcome! To join the event, please register below.

About event

Bring your eval problems. We'll screen-share, look at your failure cases together, and suggest metrics that actually track quality.

  • Grading rubrics vs. pairwise comparisons
  • Building a golden set from production traffic
  • LLM-as-judge pitfalls

Totally free, totally casual. Link is shared after you register.

Share this event

Discussion

Sign in or RSVP to join the conversation.Sign in

No comments yet

Start the conversation — hosts and guests will see it here.