You Need A Theory of Victory - by Jason Hausenloy

The cause of AI safety is losing. Consider asking: how can we win?

Note: The majority of this post is adapted from a talk I gave recently. These do not represent the views of my employer. Scroll around the organizations on this cute AI safety map. Think about, or ask, how does their work help with AI safety? My guess is that, maybe some won’t know, but most would say “X of our actions will lead to Y self-evidently good outcome.” Maybe, they’ll say, if we measure model capabilities well (we have the graph), policymakers will wake up and see AIs are improving quickly, and get their act together. In the best case, we could become a neutral third-party…

saved by

• Jason Chin

related reading

• You Need A Theory of Victory - by Jason Hausenloyfirstscattering.com
• The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
• The Case Against AI Control Research — LessWronglesswrong.com
• The Artificiality of Alignmentjoinreboot.org
• Why AI Will Save the World | Andreessen Horowitza16z.com
• Your Solution Doesn't Know Your Problem Existsblog.atlascomputing.org
• Racing through a minefield: the AI deployment problemcold-takes.com
• Building Technology to Drive AI Governancebounded-regret.ghost.io
• AI Safety Seems Hard to Measurecold-takes.com
• AI Safety for Fleshy Humans: a whirlwind touraisafety.dance
• Post 47: How I Formed My Own Views About AI Safety - Neel Nandaneelnanda.io
• AI governance needs a theory of victory | Convergence Analysisconvergenceanalysis.org