LESSWRONGTags
LW

AI Capabilities

EditHistory
Discussion (1)
Help improve this page (1 flag)
EditHistory
Discussion (1)
Help improve this page (1 flag)
AI Capabilities
Random Tag
Contributors
4plex

AI Capabilities are the growing abilities of AIs to act effectively in increasingly complex environments. It is often compared to to AI Alignment, which refers to efforts to ensure that these effective actions taken by AIs are also intended by the creators and beneficial to humanity.

Posts tagged AI Capabilities
9
134EfficientZero: human ALE sample-efficiency w/MuZero+self-supervisedΩ
gwern
2y
Ω
52
7
60A small update to the Sparse Coding interim research reportΩ
Lee Sharkey, Dan Braun, beren
2mo
Ω
5
5
288EfficientZero: How It WorksΩ
1a3orn
2y
Ω
48
5
58Competitive programming with AlphaCode
Algon
1y
36
3
352What DALL-E 2 can and cannot do
Swimmer963 (Miranda Dixon-Luinenburg)
1y
303
3
277Is AI Progress Impossible To Predict?
alyssavance
1y
39
3
93Meta AI announces Cicero: Human-Level Diplomacy play (with dialogue)
Jacy Reese Anthis
7mo
64
3
34What will the scaled up GATO look like? (Updated with questions)
Amal
8mo
20
3
16[Crosspost] AlphaTensor, Taste, and the Scalability of AI
jamierumbelow
8mo
4
3
15DeepMind on Stratego, an imperfect information game
sanxiyn
8mo
9
3
10Devil's Advocate: Adverse Selection Against Conscientiousness
lionhearted (Sebastian Marshall)
19d
2
2
149Request: stop advancing AI capabilities
So8res
21d
23
2
146A Year of AI Increasing AI Progress
ThomasW
6mo
3
2
117We have achieved Noob Gains in AIΩ
phdead
1y
Ω
20
2
100Interpreting Yudkowsky on Deep vs Shallow KnowledgeΩ
adamShimi
2y
Ω
32
Load More (15/85)
Add Posts