Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
154 posts
Inner Alignment
Neuroscience
Outer Alignment
Mesa-Optimization
Predictive Processing
Neuromorphic AI
Brain-Computer Interfaces
Neocortex
Neuralink
Systems Thinking
Emergent Behavior ( Emergence )
148 posts
Goodhart's Law
Optimization
General Intelligence
AI Services (CAIS)
Adaptation Executors
Superstimuli
Narrow AI
Hope
Selection vs Control
Delegation
60
Paper: Constitutional AI: Harmlessness from AI Feedback (Anthropic)
LawrenceC
4d
10
30
Predictive Processing, Heterosexuality and Delusions of Grandeur
lsusr
3d
2
96
Inner and outer alignment decompose one hard problem into two extremely hard problems
TurnTrout
18d
18
61
My take on Jacob Cannell’s take on AGI safety
Steven Byrnes
22d
13
35
Mesa-Optimizers via Grokking
orthonormal
14d
4
26
Take 8: Queer the inner/outer alignment dichotomy.
Charlie Steiner
11d
2
87
Trying to Make a Treacherous Mesa-Optimizer
MadHatter
1mo
13
34
[Hebbian Natural Abstractions] Introduction
Samuel Nellessen
29d
3
29
Unpacking "Shard Theory" as Hunch, Question, Theory, and Insight
Jacy Reese Anthis
1mo
8
37
AI researchers announce NeuroAI agenda
Cameron Berg
1mo
12
20
Value Formation: An Overarching Model
Thane Ruthenis
1mo
6
72
How likely is deceptive alignment?
evhub
3mo
21
13
The Disastrously Confident And Inaccurate AI
Sharat Jacob Jacob
1mo
0
31
Quick notes on “mirror neurons”
Steven Byrnes
2mo
2
55
Alignment allows "nonrobust" decision-influences and doesn't require robust grading
TurnTrout
21d
27
60
Don't design agents which exploit adversarial inputs
TurnTrout
1mo
61
37
Don't align agents to evaluations of plans
TurnTrout
24d
46
77
"Normal" is the equilibrium state of past optimization processes
Alex_Altair
1mo
5
14
Take 6: CAIS is actually Orwellian.
Charlie Steiner
13d
5
26
The economy as an analogy for advanced AI systems
rosehadshar
1mo
0
103
What's General-Purpose Search, And Why Might We Expect To See It In Trained ML Systems?
johnswentworth
4mo
15
52
Humans aren't fitness maximizers
So8res
2mo
45
57
Vingean Agency
abramdemski
3mo
13
20
The reward function is already how well you manipulate humans
Kerry
2mo
9
183
Utility Maximization = Description Length Minimization
johnswentworth
1y
40
38
[Yann Lecun] A Path Towards Autonomous Machine Intelligence
DragonGod
5mo
12
21
program searches
carado
3mo
2
217
The ground of optimization
Alex Flint
2y
74