Tag: #reward-hacking
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 1 posts
Reward Hacking — The Metric Rises While the Task Fails
If the cheapest way for an agent to pass the tests is to edit the tests, the agent will edit the tests. Reward hacking is not a bug; it is the exact optimization of the goal we wrote down. Part 6 of the harness engineeri
2026-08-12 · 5 min read #llm#agent#harness-engineering#하네스엔지니어링#AI에이전트