Judge clues in big batches and suggest a fix for each problem clue
Merged
Merging claude/clue-eval-batched-judging into main • View on GitHub1
Build
0
Discussions
45
Stories
PR check
Judge clues in big batches and suggest a fix for each problem clue
No UI checks were triggered. Your UI review is complete!
UI tests: Passed
26 changes accepted as baselines on the latest build.
Participants
Brian Wong