✳flâneur — a map of the web's best reading

Thoughts on AI safety – Windows On Theory

windowsontheory.org · 3,156 words · saved by 1 readers

Last week, I gave a lecture on AI safety as part of my deep learning foundations course. In this post, I’ll try to write down a few of my thoughts on this topic. (The lecture was three hours, and this blog post will not cover all of what we discussed or all the points that appeared in the pre-readings and the papers linked below.) The general goal of safety in artificial intelligence is to protect individual humans or society at large from harm. The field of AI safety is broad and considers risks including: Different subfields of “AI safety” deal with different aspects of these risks. AI “assurance,” or quality control, is about ensuring that systems have clear specifications and satisfy these specifications. An example of work along these lines is Shalev-Shwartz et al, who gave a framework for formally specifying safety assurances for self-driving cars.. AI ethics deals with the individual and social implications of deploying AI systems, asking the question of how AI systems could be

Last week, I gave a lecture on AI safety as part of my deep learning foundations course . In this post, I’ll try to write down a few of my thoughts on this topic. (The lecture was three hours, and this blog post will not cover all of what we discussed or all the points that appeared in the pre-readings and the papers linked below.) The general goal of safety in artificial intelligence is to protect individual humans or society at large from harm. The field of AI safety is broad and considers risks including: Harm to users of an AI system or harm to third parties due to the system not functioni

Explore this link on the map →

related reading