Your Evals Have No Tests
15 of 19 escaped · 79% escape rate on the sample run
A green eval suite isn't evidence your agent works — it's the absence of evidence. Mutation testing shows you exactly how blind your evals really are.
Tag
#evals
1 post
Tag
1 post
15 of 19 escaped · 79% escape rate on the sample run
A green eval suite isn't evidence your agent works — it's the absence of evidence. Mutation testing shows you exactly how blind your evals really are.