AI ALIGNMENT FORUM
AF

Recent Activity

42why assume AGIs will optimize for fixed goals?

nostalgebraist, Rob Bensinger

3y

3

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

Charbel-Raphael Segerie, Diego Dorn, Peter Barnett

1y

2

7Egan's Theorem?

5y

7

51Have LLMs Generated Novel Insights?

Abram Demski, Cole Wyeth, Kaj Sotala

3mo

19

40Seriously, what goes wrong with "reward the agent when it makes you smile"?

Alex Turner, johnswentworth

3y

13

14Is weak-to-strong generalization an alignment technique?

3mo

1

9What is the most impressive game LLMs can play well?

4mo

8

4How counterfactual are logical counterfactuals?

5mo

9

16Are You More Real If You're Really Forgetful?

Thane Ruthenis, Charlie Steiner

6mo

4

6Why not tool AI?

smithee, Ben Pace

6y

2

68Why is o1 so deceptive?

Abram Demski, Sahil

8mo

14

7Is there any rigorous work on using anthropic uncertainty to prevent situational awareness / deception?

David Scott Krueger

8mo

5