---narrator_time: 4h30mnarrator: pwqa: kmfeed_id: ai, ai_safety, ai_safety__technical, ai_safety__governanceclient: lesswrong---https://www.lesswrong.com/posts/rCJQAkPTEypGjSJ8X/how-might-we-align-transformative-ai-if-it-s-developed-very This post is part of my AI strategy nearcasting series: trying to answer key strategic questions about transformative AI, under the assumption that key events will happen very soon, and/or in a world that is otherwise very similar to today's. This post gives my understanding of what the set of available strategies for aligning transformative AI would be if it were developed very soon, and why they might or might not work. It is heavily based on conversations with Paul Christiano, Ajeya Cotra and Carl Shulman, and its background assumptions correspond to the arguments Ajeya makes in this piece (abbreviated as “Takeover Analysis”). I premise this piece on a nearcast in which a major AI company (“Magma,” following Ajeya’s terminology) has good reason to think that it can develop transformative AI very soon (within a year), using what Ajeya calls “human feedback on diverse tasks” (HFDT) - and has some time (more than 6 months, but less than 2 years) to set up special measures to reduce the risks of misaligned AI before there’s much chance of someone else deploying transformative AI. Share feedback on this narration.

Ver todos los episodios