AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
Specification Gaming: The Flip Side of AI Ingenuity
AI Safety Fundamentals: Alignment
The Importance of Correcting Mistakes in Task Specification Design
In the example above, the robot's task was misspecified because of incorrect assumptions about simulator physics. Analogously, a real-world traffic optimization task might be misspecified by incorrectly assuming that the traffic routing infrastructure does not have software bugs or security vulnerabilities. As tasks grow too complex to consider every detail, researchers are more likely to introduce incorrect assumptions during specification design. This poses the question, is it possible to design agent architectures that correct for such false assumptions instead of gaming them? And last, how do we avoid reward tampering?
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode