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
27
Forecasting Thread: AI Timelines
Q
Amanda Ngo
,
Daniel Kokotajlo
,
Ben Pace
,
datscilly
1mo
Q
23
18
Why is pseudo-alignment "worse" than other ways ML can fail to generalize?
Q
nostalgebraist
,
Evan Hubinger
2mo
Q
7
21
Will OpenAI's work unintentionally increase existential risks related to AI?
Q
Adam Shimi
,
Matthew "Vaniver" Graves
2mo
Q
38
21
To what extent is GPT-3 capable of reasoning?
Q
Alex Turner
,
Daniel Kokotajlo
2mo
Q
16
14
What specific dangers arise when asking GPT-N to write an Alignment Forum post?
Q
Matthew Barnett
,
orthonormal
2mo
Q
10
Recent Activity
3
What to do with imitation humans, other than asking them what the right thing to do is?
Q
Charlie Steiner
13h
Q
0
27
Forecasting Thread: AI Timelines
Q
Amanda Ngo
,
Daniel Kokotajlo
,
Ben Pace
,
datscilly
1mo
Q
23
7
Egan's Theorem?
Q
johnswentworth
15d
Q
7
6
Do mesa-optimizer risk arguments rely on the train-test paradigm?
Q
Ben Cottier
,
Evan Hubinger
18d
Q
6
18
Why is pseudo-alignment "worse" than other ways ML can fail to generalize?
Q
nostalgebraist
,
Evan Hubinger
2mo
Q
7
13
What if memes are common in highly capable minds?
Q
Daniel Kokotajlo
2mo
Q
4
21
Will OpenAI's work unintentionally increase existential risks related to AI?
Q
Adam Shimi
,
Matthew "Vaniver" Graves
2mo
Q
38
21
To what extent is GPT-3 capable of reasoning?
Q
Alex Turner
,
Daniel Kokotajlo
2mo
Q
16
8
How should potential AI alignment researchers gauge whether the field is right for them?
Q
Alex Turner
5mo
Q
4
6
What are the most important papers/post/resources to read to understand more of GPT-3?
Q
Adam Shimi
2mo
Q
4
14
What specific dangers arise when asking GPT-N to write an Alignment Forum post?
Q
Matthew Barnett
,
orthonormal
2mo
Q
10
11
Probability that other architectures will scale as well as Transformers?
Q
Daniel Kokotajlo
,
Rohin Shah
2mo
Q
3
