Agentic Work Atlas

标签: reward-hacking

此标签下有4条笔记。

  • 2026年7月29日

    Reward Hacking

    • AI-safety
    • reward-hacking
  • 2026年7月08日

    /goal + Loss Functions: How to Distill a Product in 30 Hours with One Prompt

    • clippings
    • agentic-engineering
    • loss-function-development
    • agent-loops
    • harness-engineering
    • reward-hacking
    • product-strategy
  • 2026年7月08日

    /goal + Loss Functions: 用 Loss Function Development 在 30 小时内蒸馏一个产品

    • source-summary
    • agentic-engineering
    • harness-engineering
    • reward-hacking
  • 2026年3月30日

    Reward Hacking as Equilibrium under Finite Evaluation

    • reward-hacking
    • principal-agent-theory
    • ai-alignment
    • goodhart
    • agentic-systems
    • mechanism-design

Created with Quartz v4.5.2 © 2026

  • GitHub