AI alignment

Applied to Alignment & Capabilities: What's the difference? 1mo ago

Applied to Apply to a small iteration of MLAB to be run in Oxford 1mo ago

Applied to Origin and alignment of goals, meaning, and morality 1mo ago

Applied to [Crosspost] AI Regulation May Be More Important Than AI Alignment For Existential Safety 1mo ago

Applied to Why Is No One Trying To Align Profit Incentives With Alignment Research? 1mo ago

Applied to Summary of “The Precipice” (2 of 4): We are a danger to ourselves 1mo ago

Applied to What do we know about Mustafa Suleyman's position on AI Safety? 1mo ago

Applied to Safety-First Agents/Architectures Are a Promising Path to Safe AGI 2mo ago

Applied to 3 levels of threat obfuscation 2mo ago

Applied to If AIs had subcortical brain simulation, would that solve the alignment problem? 2mo ago

Applied to AXRP Episode 24 - Superalignment with Jan Leike 2mo ago

Applied to "The Universe of Minds" - call for reviewers (Seeds of Science) 2mo ago

Applied to Carl Shulman on AI takeover mechanisms (& more): Part II of Dwarkesh Patel interview for The Lunar Society 2mo ago

Applied to [Crosspost] An AI Pause Is Humanity's Best Bet For Preventing Extinction (TIME) 2mo ago

Applied to I'm interviewing Jan Leike, co-lead of OpenAI's new Superalignment project. What should I ask him? 2mo ago

Applied to Train for incorrigibility, then reverse it (Shutdown Problem Contest Submission) 2mo ago

Applied to A simple way of exploiting AI's coming economic impact may be highly-impactful 2mo ago

Applied to Winners of AI Alignment Awards Research Contest 2mo ago

Applied to What new psychology research could best promote AI safety & alignment research? 2mo ago