Godzilla Strategies - LessWrong
Clutching a bottle of whiskey in one hand and a shotgun in the other, John scoured the research literature for ideas... He discovered several papers that described software-assisted hardware recovery…
x Godzilla Strategies — LessWrong "Why Not Just..." AI-Assisted Alignment AI Frontpage 176 Godzilla Strategies by johnswentworth 11th Jun 2022 AI Alignment Forum 4 min read 72 176 Ω 50 Clutching a bottle of whiskey in one hand and a shotgun in the other, John scoured the research literature for ideas... He discovered several papers that described software-assisted hardware recovery. The basic idea was simple: if hardware suffers more transient failures as it gets smaller, why not allow software to detect erroneous computations and re-execute them? This idea seemed promising until John realized
Explore this link on the map →related reading
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- What failure looks like — LessWronglesswrong.com
- Where I agree and disagree with Eliezer — LessWronglesswrong.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Another (outer) alignment failure story — AI Alignment Forumalignmentforum.org
- Shah and Yudkowsky on alignment failures — LessWronglesswrong.com
- A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
- Fields that I reference when thinking about AI takeover prevention — LessWronglesswrong.com
- Critical review of Christiano's disagreements with Yudkowsky — LessWronglesswrong.com
- The Alignment Problem — LessWronglesswrong.com
- AI Pause Will Likely Backfire — EA Forumforum.effectivealtruism.org