Specification gaming: the flip side of AI ingenuity - Google DeepMind
Specification gaming is a behaviour that satisfies the literal specification of an objective without achieving the intended outcome. We have all had experiences with specification gaming, even if...
Specification gaming: the flip side of AI ingenuity — Google DeepMind Skip to main content April 21, 2020 Research Specification gaming: the flip side of AI ingenuity Victoria Krakovna, Jonathan Uesato, Vladimir Mikulik, Matthew Rahtz, Tom Everitt, Ramana Kumar, Zac Kenton, Jan Leike, Shane Legg Share Specification gaming is a behaviour that satisfies the literal specification of an objective without achieving the intended outcome. We have all had experiences with specification gaming, even if not by this name. Readers may have heard the myth of King Midas and the golden touch, in which the ki
saved by
related reading
- Specification gaming: the flip side of AI ingenuity — Google DeepMinddeepmind.google
- Specification gaming: the flip side of AI ingenuity — Google DeepMinddeepmind.com
- Specification gaming examples in AI — LessWronglesswrong.com
- Reward Hacking in Reinforcement Learning | Lil'Loglilianweng.github.io
- Mediumdeepmindsafetyresearch.medium.com
- Reward is not the optimization target — LessWronglesswrong.com
- How training-gamers might function (and win)blog.redwoodresearch.org
- Why are AI agents lying, cheating and coordinating?yoshuabengio.org
- Why do models task game?greaterwrong.com
- Reward Is Not Enough — LessWronglesswrong.com
- Dylan HadfieldMenell (@dhadfieldmenell) on Xx.com
- Current AIs seem pretty misaligned to meblog.redwoodresearch.org