Why Not Just Outsource Alignment Research To An AI? — LessWrong

Warmup: The Expert If you haven’t seen “The Expert” before, I recommend it as a warmup for this post: …

x Why Not Just Outsource Alignment Research To An AI? — LessWrong "Why Not Just..." AI Frontpage 162 Why Not Just Outsource Alignment Research To An AI? by johnswentworth 9th Mar 2023 AI Alignment Forum 11 min read 50 162 Ω 47 Warmup: The Expert If you haven’t seen “The Expert” before, I recommend it as a warmup for this post: The Client: “We need you to draw seven red lines, all strictly perpendicular. Some with green ink, some with transparent. Can you do that?” (... a minute of The Expert trying to explain that, no, he cannot do that, nor can anyone else…) The Client: “So in principle, this

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• Can we safely automate alignment research? - Joe Carlsmithjoecarlsmith.com
• Current AIs seem pretty misaligned to me — LessWronglesswrong.com
• Tips for Empirical Alignment Research — AI Alignment Forumalignmentforum.org
• AGI Ruin: A List of Lethalities — LessWronglesswrong.com
• Current AIs seem pretty misaligned to meblog.redwoodresearch.org
• Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
• Automated Alignment is Harder Than You Think — LessWronglesswrong.com
• Sequent: Scale and Automation for Higher Confidence in Alignment — Sequentsequent.org
• A minimal viable product for alignment - by Jan Leikealigned.substack.com
• The Field of AI Alignment: A Postmortem, and What To Do About It — LessWronglesswrong.com
• [2605.06390] Automated alignment is harder than you thinkarxiv.org