Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
1125 posts
AI
Research Agendas
AI Timelines
Value Learning
AI Takeoff
Embedded Agency
Eliciting Latent Knowledge (ELK)
Community
Reinforcement Learning
Iterated Amplification
Debate (AI safety technique)
Game Theory
321 posts
Conjecture (org)
GPT
Oracle AI
Interpretability (ML & AI)
Myopia
Language Models
OpenAI
AI Boxing (Containment)
Machine Learning (ML)
DeepMind
Acausal Trade
Scaling Laws
503
(My understanding of) What Everyone in Technical Alignment is Doing and Why
Thomas Larsen
3mo
83
486
What 2026 looks like
Daniel Kokotajlo
1y
98
409
Discussion with Eliezer Yudkowsky on AGI interventions
Rob Bensinger
1y
257
334
EfficientZero: How It Works
1a3orn
1y
42
315
Two-year update on my personal AI timelines
Ajeya Cotra
4mo
60
297
Why Agent Foundations? An Overly Abstract Explanation
johnswentworth
9mo
54
296
Are we in an AI overhang?
Andy Jones
2y
109
285
On how various plans miss the hard bits of the alignment challenge
So8res
5mo
81
276
Fun with +12 OOMs of Compute
Daniel Kokotajlo
1y
78
271
Reward is not the optimization target
TurnTrout
4mo
97
265
The Plan
johnswentworth
1y
77
265
Ngo and Yudkowsky on alignment difficulty
Eliezer Yudkowsky
1y
143
265
An overview of 11 proposals for building safe advanced AI
evhub
2y
36
263
DeepMind: Generally capable agents emerge from open-ended play
Daniel Kokotajlo
1y
53
759
Simulators
janus
3mo
103
494
chinchilla's wild implications
nostalgebraist
4mo
114
422
A Mechanistic Interpretability Analysis of Grokking
Neel Nanda
4mo
39
410
DeepMind alignment team opinions on AGI ruin arguments
Vika
4mo
34
324
The Parable of Predict-O-Matic
abramdemski
3y
42
307
A challenge for AGI organizations, and a challenge for readers
Rob Bensinger
19d
30
255
New Scaling Laws for Large Language Models
1a3orn
8mo
21
254
We Are Conjecture, A New Alignment Research Startup
Connor Leahy
8mo
24
253
Common misconceptions about OpenAI
Jacob_Hilton
3mo
138
248
Mysteries of mode collapse
janus
1mo
35
239
The Plan - 2022 Update
johnswentworth
19d
33
227
Chris Olah’s views on AGI safety
evhub
3y
38
223
Conjecture: a retrospective after 8 months of work
Connor Leahy
27d
9
222
The Singular Value Decompositions of Transformer Weight Matrices are Highly Interpretable
beren
22d
27