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
35
Seriously, what goes wrong with "reward the agent when it makes you smile"?
Q
Alex Turner
,
johnswentworth
4mo
Q
12
22
Misc. questions about EfficientZero
Q
Daniel Kokotajlo
1y
Q
7
41
Forecasting Thread: AI Timelines
Q
Amanda Ngo
,
Daniel Kokotajlo
,
Ben Pace
,
datscilly
2y
Q
29
36
why assume AGIs will optimize for fixed goals?
Q
nostalgebraist
,
Rob Bensinger
6mo
Q
0
21
Why is pseudo-alignment "worse" than other ways ML can fail to generalize?
Q
nostalgebraist
,
Evan Hubinger
2y
Q
8
Recent Activity
3
Updates on scaling laws for foundation models from ' Transcending Scaling Laws with 0.1% Extra Compute'
Q
Nick_Greig
12d
Q
1
10
List of good AI safety project ideas?
Q
Aryeh Englander
2y
Q
5
7
Which AI Safety research agendas are the most promising?
Q
Chris_Leong
5mo
Q
1
35
Seriously, what goes wrong with "reward the agent when it makes you smile"?
Q
Alex Turner
,
johnswentworth
4mo
Q
12
15
What are the most plausible "AI Safety warning shot" scenarios?
Q
Daniel Kokotajlo
,
Paul Christiano
3y
Q
4
4
What's a good probability distribution family (e.g. "log-normal") to use for AGI timelines?
Q
David Scott Krueger
8mo
Q
2
22
Misc. questions about EfficientZero
Q
Daniel Kokotajlo
1y
Q
7
41
Forecasting Thread: AI Timelines
Q
Amanda Ngo
,
Daniel Kokotajlo
,
Ben Pace
,
datscilly
2y
Q
29
36
why assume AGIs will optimize for fixed goals?
Q
nostalgebraist
,
Rob Bensinger
6mo
Q
0
16
What if memes are common in highly capable minds?
Q
Daniel Kokotajlo
2y
Q
5
10
What to include in a guest lecture on existential risks from AI?
Q
Aryeh Englander
8mo
Q
2
21
Why is pseudo-alignment "worse" than other ways ML can fail to generalize?
Q
nostalgebraist
,
Evan Hubinger
2y
Q
8