AI ALIGNMENT FORUM
AF

Wikitags

AI Risk

Edited by brook, Ben Pace last updated 2nd Nov 2022

AI Risk is analysis of the risks associated with building powerful AI systems.

Related: AI, Orthogonality thesis, Complexity of value, Goodhart's law, Paperclip maximiser

Subscribe
1
Subscribe
1
Discussion0
Discussion0
Posts tagged AI Risk
147AGI Ruin: A List of Lethalities
Eliezer Yudkowsky
3y
144
106What failure looks like
Paul Christiano
6y
28
18Specification gaming examples in AI
Victoria Krakovna
7y
8
29An artificially structured argument for expecting AGI ruin
Rob Bensinger
2y
2
217Where I agree and disagree with Eliezer
Paul Christiano
3y
59
64Discussion with Eliezer Yudkowsky on AGI interventions
Rob Bensinger, Eliezer Yudkowsky
4y
106
20Intuitions about goal-directed behavior
Rohin Shah
7y
5
6"Corrigibility at some small length" by dath ilan
Christopher King
2y
1
98On how various plans miss the hard bits of the alignment challenge
Nate Soares
3y
48
50AGI in sight: our look at the game board
Andrea Miotti, Gabriel Alfour
2y
12
54Conjecture internal survey: AGI timelines and probability of human extinction from advanced AI
Maris Sala
2y
0
24Epistemological Framing for AI Alignment Research
Adam Shimi
4y
7
39What can the principal-agent literature tell us about AI risk?
apc
5y
11
23Open Problems in AI X-Risk [PAIS #5]
Dan H, TW123
3y
2
115How AI Takeover Might Happen in 2 Years
Josh Clymer
5mo
12
Load More (15/281)
Add Posts