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 not by this name. Readers may have heard the myth of King Midas and the golden touch, in which the king asks that anything he touches be turned to gold - but soon finds that even food and drink turn to metal in his hands. In the real world, when rewarded for doing well on a homework assignment, a student might copy another student to get the right answers, rather than learning the material - and thus exploit a loophole in the task specification.
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
Explore this link on the map →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
- Learning through human feedback — Google DeepMinddeepmind.google
- 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
- Current AIs seem pretty misaligned to me — LessWronglesswrong.com
- Reward Is Not Enough — LessWronglesswrong.com
- A Toy Environment For Exploring Reasoning About Reward — LessWronglesswrong.com
- Recontextualization Mitigates Specification Gaming Without Modifying the Specification — LessWronglesswrong.com
- Metagaming matters for training, evaluation, and oversightalignment.openai.com