Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
384 posts
AI risk
AI safety
AI forecasting
Artificial intelligence
Eliezer Yudkowsky
Paul Christiano
Swiss Existential Risk Initiative
AI takeoff
Digital person
Ethics of artificial intelligence
Dual-use
Epoch
178 posts
AI alignment
49
High-level hopes for AI alignment
Holden Karnofsky
21h
1
66
AGI Timelines in Governance: Different Strategies for Different Timeframes
simeon_c
1d
17
49
We should say more than “x-risk is high”
OllieBase
4d
6
30
How important are accurate AI timelines for the optimal spending schedule on AI risk interventions?
Tristan Cook
4d
0
285
Pre-Announcing the 2023 Open Philanthropy AI Worldviews Contest
Jason Schukraft
29d
18
78
AI Safety Seems Hard to Measure
Holden Karnofsky
9d
2
165
A challenge for AGI organizations, and a challenge for readers
RobBensinger
19d
13
28
How would you estimate the value of delaying AGI by 1 day, in marginal GiveWell donations?
AnonymousAccount
4d
19
14
What we owe the microbiome
TeddyW
3d
0
77
Thoughts on AGI organizations and capabilities work
RobBensinger
13d
7
28
Existential AI Safety is NOT separate from near-term applications
stecas
7d
9
26
Questions about AI that bother me
Eleni_A
7d
5
8
Who will be in charge once alignment is achieved?
trurl
4d
2
37
ChatGPT interviewed on TV
Will Aldred
11d
1
136
Lessons learned from talking to >100 academics about AI safety
mariushobbhahn
2mo
17
94
Alignment 201 curriculum
richard_ngo
2mo
8
154
How might we align transformative AI if it’s developed very soon?
Holden Karnofsky
3mo
16
7
Share your requests for ChatGPT
Kate Tran
15d
4
72
7 traps that (we think) new alignment researchers often fall into
Akash
2mo
13
36
The Vitalik Buterin Fellowship in AI Existential Safety is open for applications!
Cynthia Chen
2mo
0
49
Public-facing Censorship Is Safety Theater, Causing Reputational Damage
Yitz
2mo
7
32
A stubborn unbeliever finally gets the depth of the AI alignment problem
aelwood
2mo
7
44
EA’s brain-over-body bias, and the embodied value problem in AI alignment
Geoffrey Miller
3mo
1
14
My summary of “Pragmatic AI Safety”
Eleni_A
1mo
0
38
Two reasons we might be closer to solving alignment than it seems
Kat Woods
2mo
18
12
You won’t solve alignment without agent foundations
Samin
1mo
0
40
The religion problem in AI alignment
Geoffrey Miller
3mo
27
58
The alignment problem from a deep learning perspective
richard_ngo
4mo
0