DEVLOG #08 - I needed an A/B test for model mistakes
The main idea in SL-LLM-R is to test a possible repair from the exact state before a model mistake happened. I replay the situation once normally and once with only one repair changed. Comparing those two runs is much more useful than seeing a better answer later and guessing that the repair caused it.
Comments 0
No comments yet. Be the first!
Sign in to join the conversation.