LESSWRONGTags
LW

AI Capabilities

EditHistorySubscribe
Discussion (1)
Help improve this page (1 flag)
EditHistorySubscribe
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
Most Relevant
9
134EfficientZero: human ALE sample-efficiency w/MuZero+self-supervisedΩ
gwern
1y
Ω
52
5
289EfficientZero: How It WorksΩ
1a3orn
1y
Ω
48
5
58Competitive programming with AlphaCode
Algon
1y
37
3
352What DALL-E 2 can and cannot do
Swimmer963 (Miranda Dixon-Luinenburg)
10mo
305
3
277Is AI Progress Impossible To Predict?
alyssavance
10mo
38
3
93Meta AI announces Cicero: Human-Level Diplomacy play (with dialogue)
Jacy Reese Anthis
4mo
64
3
34What will the scaled up GATO look like? (Updated with questions)
Amal
5mo
20
3
16[Crosspost] AlphaTensor, Taste, and the Scalability of AI
jamierumbelow
5mo
4
3
15DeepMind on Stratego, an imperfect information game
sanxiyn
5mo
9
2
145A Year of AI Increasing AI Progress
ThomasW
3mo
3
2
115We have achieved Noob Gains in AIΩ
phdead
10mo
Ω
21
2
100Interpreting Yudkowsky on Deep vs Shallow KnowledgeΩ
adamShimi
1y
Ω
32
2
98Evaluations project @ ARC is hiring a researcher and a webdev/engineerΩ
Beth Barnes
6mo
Ω
7
2
87The alignment problem in different capability regimesΩ
Buck
2y
Ω
12
2
86Google's PaLM-E: An Embodied Multimodal Language Model
SandXbox
16d
7
Load More (15/69)
Add Posts