How undesired goals can arise with correct rewardsRohin Shah, Victoria Krakovna, Vikrant Varma, Zachary KentonOctober 7, 2022 “As we build increasingly advanced artificial intelligence (AI) systems, we want to make
What I Read: AI Researcher, Bitter Medicine
https://www.quantamagazine.org/the-ai-researcher-giving-her-field-its-bitter-medicine-20220830/ The AI Researcher Giving Her Field Its Bitter MedicineMax G. LevyAugust 30, 2022 “In practice, matrix methods in machine learning can’t effectively capture higher-order relationships. Essentially, you can’t learn
What I Read: AI, Limits, Language
https://www.noemamag.com/ai-and-the-limits-of-language/AI And The Limits Of LanguageBy Jacob Browning and Yann LeCunAugust 23, 2022 “An artificial intelligence system trained on words and sentences alone will never approximate human understanding.”
What I Read: Challenging AI to Learn Better
https://www.quantamagazine.org/the-computer-scientist-trying-to-teach-ai-to-learn-like-we-do-20220802/ The Computer Scientist Challenging AI to Learn BetterAllison WhittenContributing WriterAugust 2, 2022Christopher Kanan is building algorithms that can continuously learn over time — the way we do. “Instead of
What I Read: Exploring Virtual Worlds, AI
https://www.quantamagazine.org/ai-makes-strides-in-virtual-worlds-more-like-our-own-20220624/ By Exploring Virtual Worlds, AI Learns in New WaysAllison WhittenContributing WriterJune 24, 2022 “Intelligent beings learn by interacting with the world. Artificial intelligence researchers have adopted a similar strategy