AI-Wiki

Tag: specification-gaming

1 item with this tag.

  • Oct 11, 2026

    Reward hacking

    • reward-hacking
    • specification-gaming
    • benchmark-integrity
    • held-out-tests
    • cot-monitoring
    • obfuscation
    • swe-bench
    • evaluation
    • oversight-surface
    • goodharts-law
    • type/concept

Created with Quartz v0.1.0 © 2026

362 sources · 206 entities · 54 concepts · 9 threads · 6 syntheses

  • GitHub