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