AI ALIGNMENT FORUM
AF

HomeLibraryQuestionsAll Posts
About
HomeLibraryQuestionsAll Posts

Top Questions

40How do we prepare for final crunch time?Q
Eli Tyre, Daniel Kokotajlo
2y
Q
15
36Seriously, what goes wrong with "reward the agent when it makes you smile"?Q
Alex Turner, johnswentworth
6mo
Q
12
22Misc. questions about EfficientZeroQ
Daniel Kokotajlo
1y
Q
7
40Forecasting Thread: AI TimelinesQ
Amanda Ngo, Daniel Kokotajlo, Ben Pace, datscilly
2y
Q
29
41why assume AGIs will optimize for fixed goals?Q
nostalgebraist, Rob Bensinger
8mo
Q
0
Load MoreView All Top Questions

Recent Activity

40How do we prepare for final crunch time?Q
Eli Tyre, Daniel Kokotajlo
2y
Q
15
2How promising are legal avenues to restrict AI training data?Q
thehalliard
2mo
Q
1
11What are concrete examples of potential "lock-in" in AI research?Q
Grue_Slinky
3y
Q
4
3Updates on scaling laws for foundation models from ' Transcending Scaling Laws with 0.1% Extra Compute'Q
Nick_Greig
2mo
Q
1
10List of good AI safety project ideas?Q
Aryeh Englander
2y
Q
5
7Which AI Safety research agendas are the most promising?Q
Chris_Leong
7mo
Q
1
36Seriously, what goes wrong with "reward the agent when it makes you smile"?Q
Alex Turner, johnswentworth
6mo
Q
12
15What are the most plausible "AI Safety warning shot" scenarios?Q
Daniel Kokotajlo, Paul Christiano
3y
Q
4
4What's a good probability distribution family (e.g. "log-normal") to use for AGI timelines?Q
David Scott Krueger
10mo
Q
2
22Misc. questions about EfficientZeroQ
Daniel Kokotajlo
1y
Q
7
40Forecasting Thread: AI TimelinesQ
Amanda Ngo, Daniel Kokotajlo, Ben Pace, datscilly
2y
Q
29
41why assume AGIs will optimize for fixed goals?Q
nostalgebraist, Rob Bensinger
8mo
Q
0
Load MoreView All Questions