Some Thoughts on Bengio's Scientist AI — LessWrong
I have two substantial concerns with Yoshua Bengio’s Scientist AI. One is that it fails to think through the consequences of success, and will fall i…
x Some Thoughts on Bengio's Scientist AI — LessWrong AI Frontpage 21 Some Thoughts on Bengio's Scientist AI by Matthew Khoriaty 26th May 2026 3 min read 4 21 Epistemic Status: I wrote this for an application then realized it might be of interest to others or spark a conversation. Yoshua Bengio and LawZero are important players in AI Safety, so I think we should have a conversation about their ideas. I have two substantial concerns with Yoshua Bengio’s Scientist AI . One is that it fails to think through the consequences of success, and will fall into the same kind of alignment failures as agen
Explore this link on the map →saved by
related reading
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- LessWronglesswrong.com
- [2502.15657] Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?arxiv.org
- Danger, AI Scientist, Danger - by Zvi Mowshowitzthezvi.substack.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- Critical review of Christiano's disagreements with Yudkowsky — LessWronglesswrong.com
- AI Safety for Fleshy Humans: a whirlwind touraisafety.dance
- Unfalsifiable stories of doom | Mechanize, Inc.mechanize.work
- Where I agree and disagree with Eliezer — LessWronglesswrong.com
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com