The limits of AI safety via debate - LessWrong
The limits of AI safety via debate • I recently participated in the AGI safety fundamentals program and this is my cornerstone project. During our re…
x The limits of AI safety via debate — LessWrong Debate (AI safety technique) AI Frontpage 36 The limits of AI safety via debate by Marius Hobbhahn 10th May 2022 AI Alignment Forum 11 min read 8 36 Ω 17 The limits of AI safety via debate I recently participated in the AGI safety fundamentals program and this is my cornerstone project. During our readings of AI safety via debate ( blog , paper ) we had an interesting discussion on its limits and conditions under which it would fail. I spent only around 5 hours writing this post and it should thus mostly be seen as food for thought rather than r
saved by
related reading
- The Machines Lack Honour — LessWronglesswrong.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- An alignment safety case sketch based on debate — LessWronglesswrong.com
- The Case Against AI Control Research — LessWronglesswrong.com
- Deep Deceptiveness — LessWronglesswrong.com
- How do we (more) safely defer to AIs? — LessWronglesswrong.com
- Anthropic Fall 2023 Debate Progress Update — AI Alignment Forumalignmentforum.org
- My personal cruxes for working on AI safety — EA Forumforum.effectivealtruism.org
- [1805.00899] AI safety via debatear5iv.labs.arxiv.org
- AI Safety for Fleshy Humans: a whirlwind touraisafety.dance
- AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org