Flaws that make AI architecture unsafe & how to fix them | Stuart Russell (2020)
Originally released June 2020. Stuart Russell, UC Berkeley professor and coauthor of the most popular AI textbook, thinks the way we approach machine learning today is fundamentally flawed.
In his new book, Human Compatible, he outlines the ‘standard model’ of AI development, in which intelligence is measured as the ability to achieve some definite, completely-known objective that we’ve stated explicitly. This is so obvious it almost doesn’t even seem like a design choice, but it is.
Unfortunately there’s a big problem with this approach: it’s incredibly hard to say exactly what you want. AI today lacks common sense, and simply does whatever we’ve asked it to. That’s true even if the goal isn’t what we really want, or the methods it’s choosing are ones we would never accept.
This ‘alignment’ problem will get more and more severe as machine learning is embedded in more and more places: recommending us news, operating power grids, deciding prison sentences, doing surgery, and fighting wars. If we’re ever to hand over much of the economy to thinking machines, we can’t count on ourselves correctly saying exactly what we want the AI to do every time.
According to Stuart, we need to redesign AI around 3 principles.
Learn more and see the full transcript on the 80,000 Hours website: https://80000hours.org/podcast/episod...
Chapters:
• Rob’s intro (00:00:00)
• The interview begins (00:19:06)
• Human Compatible: Artificial Intelligence and the Problem of Control (00:21:27)
• Principles for Beneficial Machines (00:29:25)
• AI moral rights (00:33:05)
• Humble machines (00:39:35)
• Learning to predict human preferences (00:45:55)
• Animals and AI (00:49:33)
• Enfeeblement problem (00:58:21)
• Counterarguments (01:07:09)
• Orthogonality thesis (01:24:25)
• Intelligence explosion (01:29:15)
• Policy ideas (01:38:39)
• What most needs to be done (01:50:14)
----
The 80,000 Hours Podcast features unusually in-depth conversations about the world’s most pressing problems and what you can do to solve them.
Watch video Flaws that make AI architecture unsafe & how to fix them | Stuart Russell (2020) online without registration, duration hours minute second in high quality. This video was added by user 80,000 Hours 08 October 2024, don't forget to share it with your friends and acquaintances, it has been viewed on our site 473 once and liked it 8 people.