x

LESSWRONG

LW

AI Alignment — LessWrong

AI Alignment

This page is a stub.

Add Posts

Posts tagged AI Alignment

1

18Before We Defer Research to AI: Measuring Apparent-Success-Seeking

3mo

7

1

14Natural Language Transcoders

3mo

0

1

13Gemini 2.5 Pro in the AI Village as a Natural Case Study of Compounding Misalignment

Natalia Lanzoni, irgolic, David Africa, MerlinS

2mo

0

1

8Notes on "EigenBench: A Comparative Behavioral Measure of Value Alignment"

3mo

0

1

7Recognition: when an agent counts an entity as itself

2mo

0

1

2Notes on "Patterns and problems in emerging multiagent systems"

2mo

0

1

1What If We Enforced AI Model Safety At the Level Of GPUs?

3mo

5

1

0An "Anthropic Principle" for Formulations of AI Alignment

2mo

0

Add Posts