Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
2040 posts
AI
Careers
Audio
Infra-Bayesianism
Interviews
SERI MATS
Redwood Research
Formal Proof
Organization Updates
AXRP
Adversarial Examples
Domain Theory
197 posts
AI Takeoff
AI Timelines
Dialogue (format)
DeepMind
7
Podcast: Tamera Lanham on AI risk, threat models, alignment proposals, externalized reasoning oversight, and working at Anthropic
Akash
2h
0
29
Take 12: RLHF's use is evidence that orgs will jam RL at real-world problems.
Charlie Steiner
19h
0
33
The "Minimal Latents" Approach to Natural Abstractions
johnswentworth
22h
6
40
Towards Hodge-podge Alignment
Cleo Nardo
1d
20
199
AI alignment is distinct from its near-term applications
paulfchristiano
7d
5
108
The next decades might be wild
Marius Hobbhahn
5d
21
15
Solution to The Alignment Problem
Algon
1d
0
95
Trying to disambiguate different questions about whether RLHF is “good”
Buck
6d
39
22
Event [Berkeley]: Alignment Collaborator Speed-Meeting
AlexMennen
1d
2
54
High-level hopes for AI alignment
HoldenKarnofsky
5d
3
39
Proper scoring rules don’t guarantee predicting fixed points
Johannes_Treutlein
4d
2
207
A challenge for AGI organizations, and a challenge for readers
Rob Bensinger
19d
30
73
Revisiting algorithmic progress
Tamay
7d
6
51
«Boundaries», Part 3b: Alignment problems in terms of boundaries
Andrew_Critch
6d
2
143
Updating my AI timelines
Matthew Barnett
15d
40
21
How important are accurate AI timelines for the optimal spending schedule on AI risk interventions?
Tristan Cook
4d
2
128
Planes are still decades away from displacing most bird jobs
guzey
25d
13
54
Human-level Diplomacy was my fire alarm
Lao Mein
27d
15
296
DeepMind alignment team opinions on AGI ruin arguments
Vika
4mo
34
98
Caution when interpreting Deepmind's In-context RL paper
Sam Marks
1mo
6
56
Disagreement with bio anchors that lead to shorter timelines
Marius Hobbhahn
1mo
16
144
Why I think strong general AI is coming soon
porby
2mo
126
242
Two-year update on my personal AI timelines
Ajeya Cotra
4mo
60
33
Human-level Full-Press Diplomacy (some bare facts).
Cleo Nardo
28d
7
195
What do ML researchers think about AI in 2022?
KatjaGrace
4mo
33
83
Paper: Discovering novel algorithms with AlphaTensor [Deepmind]
LawrenceC
2mo
18
97
How might we align transformative AI if it’s developed very soon?
HoldenKarnofsky
3mo
17
32
Has anyone increased their AGI timelines?
Darren McKee
1mo
13