Musings on the Alignment Problem

Home
Archive
About
Combining weak-to-strong generalization with scalable oversight
A high-level view on how this new approach fits into our alignment plans
 • 
Jan Leike
11

September 2023

Self-exfiltration is a key dangerous capability
We need to measure whether LLMs could “steal” themselves
 • 
Jan Leike
18

March 2023

A proposal for importing society’s values
Building towards Coherent Extrapolated Volition with language models
 • 
Jan Leike
10

December 2022

Distinguishing three alignment taxes
The impact of different alignment taxes depends on the context
 • 
Jan Leike
5
Why I’m optimistic about our alignment approach
Some arguments in favor and responses to common objections
 • 
Jan Leike
25

September 2022

What could a solution to the alignment problem look like?
A high-level view on the elusive once-and-for-all solution
 • 
Jan Leike
7

May 2022

What is inner alignment?
An explanation using the language of machine learning
 • 
Jan Leike

March 2022

A minimal viable product for alignment
Bootstrapping a solution to the alignment problem
 • 
Jan Leike
Why I’m excited about AI-assisted human feedback
How to scale alignment techniques to hard tasks
 • 
Jan Leike
What is the alignment problem?
My attempt at clarifying a confusing topic
 • 
Jan Leike
4
© 2024 Jan Leike
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great culture