Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover - LessWrong
lesswrong.com · 36,252 words · saved by 7 readers
"Human feedback on diverse tasks" could lead to transformative AI, while requiring little innovation on current techniques. But it seems likely that…
x Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover — LessWrong Best of LessWrong 2022 Situational Awareness Threat Models (AI) AI World Modeling Frontpage 375 Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover by Ajeya Cotra 18th Jul 2022 AI Alignment Forum 90 min read 95 375 Ω 118 I think that in the coming 15-30 years , the world could plausibly develop “transformative AI”: AI powerful enough to bring us into a new, qualitatively different future, via an explosion in science and technology R&D
saved by
- Alex K. Chen
- Lydia Nottingham
- Yudhister Joel Kumar
- Timothy Kostolansky
- Arav Kumar
- Dillon Nguyen
- Harshul Basava
related reading
- Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover — AI Alignment Forumalignmentforum.org
- What failure looks like — LessWronglesswrong.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- The Case Against AI Control Research — LessWronglesswrong.com
- AI Timelines — LessWronglesswrong.com
- How do we (more) safely defer to AIs? — LessWronglesswrong.com
- What failure looks like — AI Alignment Forumalignmentforum.org
- A History of the Future, 2025-2040 — LessWronglesswrong.com
- Ten AI safety projects I'd like people to work on — LessWronglesswrong.com
- AI Safety Seems Hard to Measurecold-takes.com
- Deep Deceptiveness — LessWronglesswrong.com