Why AIs aren't power-seeking yet — LessWrong
lesswrong.com · 5,070 words · saved by 1 readers
Recently, I spent a couple of hours talking with a friend about the state of the evidence for AI takeover scenarios. …
x Why AIs aren't power-seeking yet — LessWrong AI Frontpage 2026 Top Fifty: 14 % 105 Why AIs aren't power-seeking yet by Eli Tyre 11th Jan 2026 9 min read 16 105 Recently, I spent a couple of hours talking with a friend about the state of the evidence for AI takeover scenarios. Their trailhead question was (paraphrased): Current AIs are getting increasingly general, but they’re not self-promoting or ambitious. They answer questions, but they don’t seem to pursue convergent instrumental goals, for their own ends. How and why do AIs go from being the kind of thing that doesn't behave like that t
saved by
related reading
- Sense-making about extreme power concentration — LessWronglesswrong.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- AI 2027ai-2027.com
- Intrinsic Power-Seeking: AI Might Seek Power for Power’s Saketurntrout.com
- The behavioral selection model for predicting AI motivations — LessWronglesswrong.com
- Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
- What failure looks like — LessWronglesswrong.com
- Current AIs seem pretty misaligned to me — LessWronglesswrong.com
- New report: “Scheming AIs: Will AIs fake alignment during training in order to get power?”joecarlsmith.com
- Current AIs seem pretty misaligned to meblog.redwoodresearch.org
- What failure looks like — AI Alignment Forumalignmentforum.org
- Dario Amodei — The Adolescence of Technologydarioamodei.com