“Sharp Left Turn” discourse: An opinionated review — LessWrong
The goal of this post is to discuss the so-called “sharp left turn”, the lessons that we learn from analogizing evolution to AGI development, and the claim that “capabilities generalize farther than alignment” … and the competing claims that all three of those things are complete baloney. In particular, …
x “Sharp Left Turn” discourse: An opinionated review — LessWrong Sharp Left Turn 2023 Longform Reviews AI Takeoff AI Curated 2025 Top Fifty: 14 % 228 “Sharp Left Turn” discourse: An opinionated review by Steven Byrnes 28th Jan 2025 AI Alignment Forum 38 min read 31 228 Ω 88 Summary and Table of Contents The goal of this post is to discuss the so-called “sharp left turn”, the lessons that we learn from analogizing evolution to AGI development, and the claim that “capabilities generalize farther than alignment” … and the competing claims that all three of those things are complete baloney. In pa
Explore this link on the map →related reading
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- A central AI alignment problem: capabilities generalization, and the sharp left turn — LessWronglesswrong.com
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- The Artificial Intelligence Revolution: Part 1 - Wait But Whywaitbutwhy.com
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- Planning for AGI and beyond | OpenAIopenai.com
- Unfalsifiable stories of doom | Mechanize, Inc.mechanize.work
- The Best of LessWrong — LessWronglesswrong.com
- Questions about the Future of AI - by Dwarkesh Pateldwarkesh.com
- Commentary on AGI Safety from First Principles — AI Alignment Forumalignmentforum.org
- A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
- My take on Jacob Cannell’s take on AGI safety — LessWronglesswrong.com