{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"80,000 Hours Podcast","title":"#92 – Brian Christian on the alignment problem","html":"","width":"100%","height":180,"duration":10546,"description":"Brian Christian is a bestselling author with a particular knack for accurately communicating difficult or technical ideas from both mathematics and computer science. \n\nListeners loved our episode about his book Algorithms to Live By — so when the team read his new book, The Alignment Problem, and found it to be an insightful and comprehensive review of the state of the research into making advanced AI useful and reliably safe, getting him back on the show was a no-brainer. \n\nBrian has so much of substance to say this episode will likely be of interest to people who know a lot about AI as well as those who know a little, and of interest to people who are nervous about where AI is going as well as those who aren't nervous at all. \n\nLinks to learn more, summary and full transcript.\n\nHere’s a tease of 10 Hollywood-worthy stories from the episode: \n\n• The Riddle of Dopamine: The development of reinforcement learning solves a long-standing mystery of how humans are able to learn from their experience. \n• ALVINN: A student teaches a military vehicle to drive between Pittsburgh and Lake Erie, without intervention, in the early 1990s, using a computer with a tenth the processing capacity of an Apple Watch. \n• Couch Potato: An agent trained to be curious is stopped in its quest to navigate a maze by a paralysing TV screen. \n• Pitts & McCulloch: A homeless teenager and his foster father figure invent the idea of the neural net. \n• Tree Senility: Agents become so good at living in trees to escape predators that they forget how to leave, starve, and die. \n• The Danish Bicycle: A reinforcement learning agent figures out that it can better achieve its goal by riding in circles as quickly as possible than reaching its purported destination. \n• Montezuma's Revenge: By 2015 a reinforcement learner can play 60 different Atari games — the majority impossibly well — but can’t score a single point on one game humans find tediously simple. \n• Curious Pong: Two novelty-seeking agents,...","thumbnail_url":"https://img.transistorcdn.com/VO1STE7hN95RRg9QdLo4soV2VhhbR9PF5ZZlRhDYcwE/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzQxNDAyLzE2ODM1/NDQ1NDAtYXJ0d29y/ay5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}