LESSWRONG
LW

106
Wikitags

AI Psychology

Edited by keltan, habryka last updated 29th Dec 2024

Trying to understand modern ML systems (at the moment mostly foundation models) from a top down perspective.

Analogous to Human Psychology (Top Down) vs Human Neuroscience (Bottom Up)

Subscribe
Discussion
1
Subscribe
Discussion
1
Posts tagged AI Psychology
236A Three-Layer Model of LLM Psychology
Ω
Jan_Kulveit
8mo
Ω
15
228Do Not Tile the Lightcone with Your Confused Ontology
Ω
Jan_Kulveit
3mo
Ω
27
133The Pando Problem: Rethinking AI Individuality
Ω
Jan_Kulveit
6mo
Ω
14
112Show, not tell: GPT-4o is more opinionated in images than in text
Daniel Tan, eggsyntax
6mo
41
13AXRP Episode 42 - Owain Evans on LLM Psychology
Ω
DanielFilan
4mo
Ω
0
80Studying The Alien Mind
Ω
Quentin FEUILLADE--MONTIXI, NicholasKees
2y
Ω
10
52The Stochastic Parrot Hypothesis is debatable for the last generation of LLMs
Quentin FEUILLADE--MONTIXI, Pierre Peigné
2y
21
33Preface to the Sequence on LLM Psychology
Quentin FEUILLADE--MONTIXI
2y
0
18Category-Theoretic Wanderings into Interpretability
unruly abstractions
25d
2
15Toward a taxonomy of cognitive benchmarks for agentic AGIs
Ben Smith
1y
0
15Policy Entropy, Learning, and Alignment (Or Maybe Your LLM Needs Therapy)
Ω
sdeture
4mo
Ω
6
9Does Claude Prioritize Some Prompt Input Channels Over Others?
keltan
9mo
2
6Intelligence Is Jagged
Adam Train
7mo
1
5Detailed Ideal World Benchmark
Knight Lee
8mo
2
1Static Place AI Makes Agentic AI Redundant: Multiversal AI Alignment & Rational Utopia
ank
7mo
2
Load More (15/16)
Add Posts