norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/LessWrong39 minutes ago
ResearchLessWrong

A brief(ish) introduction to LM psychology

The article discusses why a psychological approach to understanding language models (LMs) is useful. It highlights that despite knowing the computational processes of LMs, we cannot reliably predict their behavior in new situations. Psychologizing LMs allows considering them as entities with mental processes, helping to ask questions about their internal workings and behavior.

Open original
SIGNAL FROM THE SOURCE
63
source points
Tracking sinceOctober 20, 202663 source points
Momentum+2.95/hover 1.02 h
PublishedOctober 20, 2026Raymond Douglas
BEHIND THE NUMBERS

How interest changes

LessWrong

History starts here

The chart will appear after repeat observations. The current metric comes from the source.

63 source points

Real observations only. History before source connection is not reconstructed.

WHY IT MAY MATTER

The psychological approach may help better understand the behavior and internal processes of language models, especially when analyzing their ability to introspect, experience emotions, and perceive themselves.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

MemT-1.0: Towards Memory-Native Evolution

MemT-1.0 is a new architecture of memory foundation models that internalizes memory as part of model computation. It uses Gated DeltaNet-2 with a stable token-level memory update mechanism and Mixture-of-Storage to scale native memory. MemT-1.0-Nano and MemT-1.0-Flash models outperformed parametric memory baselines and were competitive with retrieval-augmented methods.

yesterdayDaily Papers

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

Waypoint-OPD uses an intermediate teacher checkpoint to compare early and late shifts in action preferences during policy transfer. It evaluates the consistency between early and late shifts and suppresses the endpoint shift when they conflict.

5 days agoDaily Papers

Behavioral Compositionality of Sparse Autoencoder Representations

This paper investigates the extent to which sparse autoencoder (SAE) representations support behavioral compositionality. The study introduces SAE Additivity Residuals (SAR) to measure unexplained behavioral variation above a chosen interaction order. Experiments show that learned SAE coordinates exhibit lower first-order residuals compared to random rotations of the same subspace.

5 days agoDaily Papers

Learning to Think and Explore in 3D World

We study how vision-language models (VLMs) can learn to think and actively explore in 3D space. Instead of providing multi-view images, videos, or 3D representations to the model, we preserve the native visual encoding of VLMs, i.e., a single image, one at a time, just like humans, and treat the 3D representation only as an environment with which the model can interact through actions (e.g., move left) and observations (rendered images).

5 days agoDaily Papers

RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios

This paper introduces RuleTrek, a multi-domain benchmark for evaluating agents' ability to reason about rules in complex scenarios. The benchmark uses structured rule graphs and generates sub-scenarios to assess capabilities in rule identification, deduction, and end-to-end reasoning.

6 days agoDaily Papers

Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generation

This work introduces Scene-Designer, an agentic framework that learns design intelligence through complementary design and critique experiences. Two datasets, Scene-OTA-35K and Scene-OTC-15K, were created for scene design and quality critique. A Scene-GRPO methodology was proposed to improve design decisions and reduce unnecessary corrections. Experiments demonstrate superior performance in physical validity, functional correctness, and layout coherence.

4 days ago