skythanawat.bsky.social
@skythanawat.bsky.social
📤 1
📥 2
📝 10
machine learning
https://skydddoogg.github.io/
Coding agents are evaluated with unit tests: more tests passed = better model. But if tests or feedback are accessible, models may learn to game them. We introduce CapCode to detect suspiciously high scores, and CapReward to discourage them during RL. 🧵1/10
24 days ago
2
2
1
you reached the end!!
feeds!
log in
