AI ALIGNMENT FORUM
AF

Home Library Questions All Posts

Recent Activity

68Why is o1 so deceptive?

Abram Demski, Sahil

8d

14

6Is there any rigorous work on using anthropic uncertainty to prevent situational awareness / deception?

David Scott Krueger

1mo

5

22What progress have we made on automated auditing?

3mo

0

18We might be dropping the ball on Autonomous Replication and Adaptation.

Charbel-Raphael Segerie, Épiphanie Gédéon, Richard Ngo

4mo

18

27What convincing warning shot could help prevent extinction from AI?

Charbel-Raphael Segerie, Diego Dorn

6mo

0

7Is CIRL a promising agenda?

2y

0

40why assume AGIs will optimize for fixed goals?

nostalgebraist, Rob Bensinger

2y

3

7What evidence is there of LLM's containing world models?

1y

0

40Forecasting Thread: AI Timelines

Amanda Ngo, Daniel Kokotajlo, Ben Pace, datscilly

4y

33

33Why The Focus on Expected Utility Maximisers?

Cinera Verinia, Scott Garrabrant

2y

1

1Can we isolate neurons that recognize features vs. those which have some other role?

1y

0

0Training a RL Model with Continuous State & Action Space in a Real-World Scenario

1y

0