AI ALIGNMENT FORUM
AF

HomeLibraryQuestionsAll Posts
About
HomeLibraryQuestionsAll Posts

Top Questions

37Seriously, what goes wrong with "reward the agent when it makes you smile"?Q
Alex Turner, johnswentworth
10mo
Q
13
31Does Agent-like Behavior Imply Agent-like Architecture?Q
Scott Garrabrant
4y
Q
2
27How Many Bits Of Optimization Can One Bit Of Observation Unlock?Q
johnswentworth, johnswentworth
1mo
Q
3
32Concave Utility QuestionQ
Scott Garrabrant
2mo
Q
36
40Forecasting Thread: AI TimelinesQ
Amanda Ngo, Daniel Kokotajlo, Ben Pace, datscilly
3y
Q
32
Load MoreView All Top Questions

Recent Activity

37Seriously, what goes wrong with "reward the agent when it makes you smile"?Q
Alex Turner, johnswentworth
10mo
Q
13
8Why don't quantilizers also cut off the upper end of the distribution?Q
Alex_Altair, Jeremy Gillen
19d
Q
1
31Does Agent-like Behavior Imply Agent-like Architecture?Q
Scott Garrabrant
4y
Q
2
27How Many Bits Of Optimization Can One Bit Of Observation Unlock?Q
johnswentworth, johnswentworth
1mo
Q
3
6Why do we care about agency for alignment?Q
Chris_Leong
1mo
Q
6
5How much do personal biases in risk assessment affect assessment of AI risks?Q
G Gordon Worley III
1mo
Q
1
32Concave Utility QuestionQ
Scott Garrabrant
2mo
Q
36
11What happens with logical induction when...Q
Donald Hobson
2mo
Q
1
40Forecasting Thread: AI TimelinesQ
Amanda Ngo, Daniel Kokotajlo, Ben Pace, datscilly
3y
Q
32
12What organizations other than Conjecture have (esp. public) info-hazard policies?Q
David Scott Krueger
3mo
Q
0
24To what extent is GPT-3 capable of reasoning?Q
Alex Turner, Daniel Kokotajlo
3y
Q
26
41why assume AGIs will optimize for fixed goals?Q
nostalgebraist, Rob Bensinger
1y
Q
1
Load MoreView All Questions