Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
76 posts
Inner Alignment
Outer Alignment
Mesa-Optimization
78 posts
Neuroscience
Predictive Processing
Neuromorphic AI
Brain-Computer Interfaces
Neocortex
Neuralink
Systems Thinking
Emergent Behavior ( Emergence )
84
Inner and outer alignment decompose one hard problem into two extremely hard problems
TurnTrout
18d
18
61
Paper: Constitutional AI: Harmlessness from AI Feedback (Anthropic)
LawrenceC
4d
10
19
Value Formation: An Overarching Model
Thane Ruthenis
1mo
6
-1
Don't you think RLHF solves outer alignment?
Raphaël S
1mo
19
41
Mesa-Optimizers via Grokking
orthonormal
14d
4
81
Trying to Make a Treacherous Mesa-Optimizer
MadHatter
1mo
13
28
Take 8: Queer the inner/outer alignment dichotomy.
Charlie Steiner
11d
2
-4
I there a demo of "You can't fetch the coffee if you're dead"?
Ram Rachum
1mo
9
60
How likely is deceptive alignment?
evhub
3mo
21
74
2-D Robustness
vlad_m
3y
8
165
Inner Alignment: Explain like I'm 12 Edition
Rafael Harth
2y
46
2
How much should we worry about mesa-optimization challenges?
sudo -i
4mo
13
22
Greed Is the Root of This Evil
Thane Ruthenis
2mo
4
7
Alignment as Game Design
Shoshannah Tekofsky
5mo
7
25
Unpacking "Shard Theory" as Hunch, Question, Theory, and Insight
Jacy Reese Anthis
1mo
8
32
Predictive Processing, Heterosexuality and Delusions of Grandeur
lsusr
3d
2
72
My take on Jacob Cannell’s take on AGI safety
Steven Byrnes
22d
13
31
AI researchers announce NeuroAI agenda
Cameron Berg
1mo
12
29
[Hebbian Natural Abstractions] Introduction
Samuel Nellessen
29d
3
40
On oxytocin-sensitive neurons in auditory cortex
Steven Byrnes
3mo
6
-2
A physicist's approach to Origins of Life
pchvykov
5mo
6
34
Quick notes on “mirror neurons”
Steven Byrnes
2mo
2
41
[Intro to brain-like-AGI safety] 2. “Learning from scratch” in the brain
Steven Byrnes
10mo
12
13
(Link) I'm Missing a Chunk of My Brain
mukashi
3mo
2
134
Inner Alignment in Salt-Starved Rats
Steven Byrnes
2y
39
13
Brain-Brain communication
Jordan
11y
22
4
A future for neuroscience
Mike Johnson
4y
12
18
FAI and the Information Theory of Pleasure
johnsonmx
7y
19