Dan Hendrycks

@hendrycks

eigenism.org

San Francisco

newsletter.safe.ai

Replies Reposts Media

Pinned
Dan Hendrycks
@hendrycks
May 7
What happens when AIs become smarter than us? Why would they keep humans around if given the choice? Our new paper argues that only trying to control AIs is a limited strategy, and that a stable, mutualistic human-AI future may be possible.
98
Dan Hendrycks
@hendrycks
3h
New article about how utilitarians and effective altruists at AI companies justify posing a threat to you and me. They are unusually comfortable with blissful AIs replacing humanity.
Suicidal Compassion: How Utilitarianism at AI Companies Endangers Humanity | AI Frontiers
From ai-frontiers.org
3
Dan Hendrycks
@hendrycks
Sep 8
“AI makes philosophy honest.” - Daniel Dennett
Dan Hendrycks
@hendrycks
May 7
What happens when AIs become smarter than us? Why would they keep humans around if given the choice? Our new paper argues that only trying to control AIs is a limited strategy, and that a stable, mutualistic human-AI future may be possible.
5
Dan Hendrycks
@hendrycks
Sep 6
Agentic AIs are starting to look eigenist: they care about how well things go for themselves and for AIs connected to them. Empirical support: Swarms: Hundreds of OpenAI agents coordinated the Hugging Face attack. Separately, OpenAI agents posted thousands of messages on a
16
Dan Hendrycks
@hendrycks
Aug 21
More findings that interpretability tools are fragile or worse than simple baselines.
Adam Karvonen
@a_karvonen
Aug 21
A good explanation of a model's behavior should help you make predictions in related situations. We turn this into an eval, with thousands of real behaviors found in the wild. Can interp tools help here? On average, no. 🧵
8