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
19
What exactly is GPT-3's base objective?
Q
Daniel Kokotajlo
,
Evan Hubinger
22d
Q
10
15
Will OpenAI's work unintentionally increase existential risks related to AI?
Q
Adam Shimi
,
Matthew "Vaniver" Graves
1y
Q
41
34
Forecasting Thread: AI Timelines
Q
Amanda Ngo
,
Daniel Kokotajlo
,
Ben Pace
,
datscilly
1y
Q
24
36
How do we prepare for final crunch time?
Q
Eli Tyre
,
Daniel Kokotajlo
8mo
Q
15
25
Suggestions of posts on the AF to review
Q
Adam Shimi
,
johnswentworth
9mo
Q
16
Recent Activity
19
What exactly is GPT-3's base objective?
Q
Daniel Kokotajlo
,
Evan Hubinger
22d
Q
10
15
Will OpenAI's work unintentionally increase existential risks related to AI?
Q
Adam Shimi
,
Matthew "Vaniver" Graves
1y
Q
41
14
What if memes are common in highly capable minds?
Q
Daniel Kokotajlo
1y
Q
4
5
Memetic hazards of AGI architecture posts
Q
Ozyrus
,
Rob Bensinger
1mo
Q
0
12
Collection of arguments to expect (outer and inner) alignment failure?
Q
Sam Clarke
2mo
Q
10
6
Why not tool AI?
Q
smithee
,
Ben Pace
3y
Q
2
34
Forecasting Thread: AI Timelines
Q
Amanda Ngo
,
Daniel Kokotajlo
,
Ben Pace
,
datscilly
1y
Q
24
6
What are good alignment conference papers?
Q
Adam Shimi
3mo
Q
2
10
How much compute was used to train DeepMind's generally capable agents?
Q
Daniel Kokotajlo
4mo
Q
6
8
Did they or didn't they learn tool use?
Q
Daniel Kokotajlo
4mo
Q
3
10
List of good AI safety project ideas?
Q
Aryeh Englander
6mo
Q
5
14
Open problem: how can we quantify player alignment in 2x2 normal-form games?
Q
Alex Turner
,
Vanessa Kosoy
6mo
Q
21
