Risks from Learned Optimization: Introduction — LessWrong

AI researchers warn that advanced machine learning systems may develop their own internal goals that don't match what we intended. This "mesa-optimiz…

x Risks from Learned Optimization: Introduction — LessWrong Risks from Learned Optimization Mesa-Optimization Inner Alignment Outer Alignment Optimization AI Risk AI Frontpage 188 Risks from Learned Optimization: Introduction by evhub , Chris van Merwijk , Vlad Mikulik , Joar Skalse , Scott Garrabrant 31st May 2019 AI Alignment Forum 14 min read 42 188 Ω 58 This is the first of five posts in the Risks from Learned Optimization Sequence based on the paper “ Risks from Learned Optimization in Advanced Machine Learning Systems ” by Evan Hubinger, Chris van Merwijk, Vladimir Mikulik, Joar Skalse,

related reading

• Risks from Learned Optimization: Introduction — AI Alignment Forumalignmentforum.org
• Risks from Learned Optimization: Introduction — AI Alignment Forumalignmentforum.org
• The Inner Alignment Problem — AI Alignment Forumalignmentforum.org
• Conditions for Mesa-Optimization — AI Alignment Forumalignmentforum.org
• Deceptively Aligned Mesa-Optimizers: It's Not Funny If I Have To Explain Itastralcodexten.com
• Mesa-Optimization — AI Alignment Forumalignmentforum.org
• Deceptive Alignment — AI Alignment Forumalignmentforum.org
• [1906.01820] Risks from Learned Optimization in Advanced Machine Learning Systemsarxiv.org
• Inner Alignment: Explain like I'm 12 Edition — LessWronglesswrong.com
• [1906.01820] Risks from Learned Optimization in Advanced Machine Learning Systemsarxiv.org
• Inner Alignment: Explain like I'm 12 Edition — LessWronglesswrong.com
• Alignment remains a hard, unsolved problem — LessWronglesswrong.com