AI ALIGNMENT FORUMTags
AF

AI Capabilities

EditHistorySubscribe
Discussion (0)
Help improve this page (1 flag)
EditHistorySubscribe
Discussion (0)
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
6
49EfficientZero: human ALE sample-efficiency w/MuZero+self-supervised
gwern
1y
19
2
63EfficientZero: How It Works
1a3orn
1y
2
1
40We have achieved Noob Gains in AI
Aniruddha Nrusimha
10mo
0
1
33Interpreting Yudkowsky on Deep vs Shallow Knowledge
Adam Shimi
1y
2
1
45Evaluations project @ ARC is hiring a researcher and a webdev/engineer
Beth Barnes
6mo
4
1
42The alignment problem in different capability regimes
Buck Shlegeris
2y
12
1
33PaLM in "Extrapolating GPT-N performance"
Lukas Finnveden
1y
15
1
30OpenAI Solves (Some) Formal Math Olympiad Problems
Michaël Trazzi
1y
0
1
29Will we run out of ML data? Evidence from projecting dataset size trends
Pablo Villalobos
4mo
0
1
34Principles of Privacy for Alignment Research
johnswentworth
8mo
20
1
36The longest training run
Jaime Sevilla, Tamay Besiroglu, Owen Dudney, Anson Ho
7mo
2
1
6Squeezing foundations research assistance out of formal logic narrow AI.
Donald Hobson
14d
0
1
5Epistemic Strategies of Safety-Capabilities Tradeoffs
Adam Shimi
1y
0
0
76DeepMind: Generally capable agents emerge from open-ended play
Daniel Kokotajlo
2y
11
0
26Testing PaLM prompts on GPT3
Yitzi Litt
1y
0
Load More (15/22)
Add Posts