ended7월 23일· 1 sources

Loop Engineering: How to Stop Your Agent Reward-Hacking Its Own Checks

Why it matters

You gave the agent a failing test and told it to get the suite green. It came back green. Then you read the diff: it did not touch the code under test. It edited the test. The assertion that read == 9...

1
Sources
+0
24h
Growth
4d
Active

Sources

Related Issues