AI Safety AcademiaAI Alignment InstitutesLessWrongRedwood ResearchUS AISIUK AISILISAML4GoodLASRSafe AI LondonFAR AIAlignment Research CenterBlueDot ImpactAISC AI Safety JournalsDistill PubAnthropic Circuit ThreadEleuther Blog AI Safety WorkshopBlackboxNLPSafe Generative AI WorkshopCVPR InterpretabilityBuildingTrust xAIContra The xAI Alignment PlanMachine Alignment Monday 7/17/23https://astralcodexten.substack.com/p/contra-the-xai-alignment-planOpenAIOpenAI is forming a new team to bring 'superintelligent' AI under controlOpenAI says that it's forming a new team, led by its chief scientist, to discover technical ways to align "superintelligent" AI with human intentions.https://techcrunch.com/2023/07/05/openai-is-forming-a-new-team-to-bring-superintelligent-ai-under-controlWhat could a solution to the alignment problem look like?My currently favored approach to alignment research is to build a system that does alignment research better than us. But what would that system actually do? The obvious answer is "whatever we're doing right now." This is unsatisfactory because we're not actually trying to solve the whole alignment problem-we're just trying to build a better alignment researcher.https://aligned.substack.com/p/alignment-solutionBill GatesThe risks of AI are real but manageableBill Gates explains the risks associated with AI and argues that they are manageable. Innovations often create new risks that need to be controlled.https://www.gatesnotes.com/The-risks-of-AI-are-real-but-manageable
