Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
734 posts
AI
Eliciting Latent Knowledge (ELK)
Infra-Bayesianism
Counterfactuals
Logic & Mathematics
Interviews
Audio
AXRP
Redwood Research
Transcripts
Formal Proof
Domain Theory
74 posts
Embedded Agency
Reinforcement Learning
Subagents
Reward Functions
EfficientZero
Robust Agents
Wireheading
AI Capabilities
Spurious Counterfactuals
Category Theory
Memetics
Tradeoffs
344
(My understanding of) What Everyone in Technical Alignment is Doing and Why
Thomas Larsen
3mo
83
325
Discussion with Eliezer Yudkowsky on AGI interventions
Rob Bensinger
1y
257
247
DeepMind: Generally capable agents emerge from open-ended play
Daniel Kokotajlo
1y
53
245
Visible Thoughts Project and Bounty Announcement
So8res
1y
104
237
larger language models may disappoint you [or, an eternally unfinished draft]
nostalgebraist
1y
29
235
The Plan
johnswentworth
1y
77
235
Ngo and Yudkowsky on alignment difficulty
Eliezer Yudkowsky
1y
143
232
AI alignment is distinct from its near-term applications
paulfchristiano
7d
5
212
ARC's first technical report: Eliciting Latent Knowledge
paulfchristiano
1y
88
212
Safetywashing
Adam Scholl
5mo
17
206
Hiring engineers and researchers to help align GPT-3
paulfchristiano
2y
14
204
Attempted Gears Analysis of AGI Intervention Discussion With Eliezer
Zvi
1y
48
198
Embedded Agents
abramdemski
4y
41
197
Optimality is the tiger, and agents are its teeth
Veedrac
8mo
31
273
EfficientZero: How It Works
1a3orn
1y
42
252
Reward is not the optimization target
TurnTrout
4mo
97
248
Humans are very reliable agents
alyssavance
6mo
35
161
Why Subagents?
johnswentworth
3y
42
145
Introduction to Cartesian Frames
Scott Garrabrant
2y
29
143
Embedded Agency (full-text version)
Scott Garrabrant
4y
15
134
EfficientZero: human ALE sample-efficiency w/MuZero+self-supervised
gwern
1y
52
114
We have achieved Noob Gains in AI
phdead
7mo
21
110
Robust Delegation
abramdemski
4y
10
105
Reward Is Not Enough
Steven Byrnes
1y
18
100
Subsystem Alignment
abramdemski
4y
12
94
Evaluations project @ ARC is hiring a researcher and a webdev/engineer
Beth Barnes
3mo
7
88
Embedded Curiosities
Scott Garrabrant
4y
1
87
The alignment problem in different capability regimes
Buck
1y
12