Musings on the Alignment Problem

Home
Archive
About
Self-exfiltration is a key dangerous capability
We need to measure whether LLMs could “steal” themselves
 • 
Jan Leike
14
New
Top
Community
A proposal for importing society’s values
Building towards Coherent Extrapolated Volition with language models
 • 
Jan Leike
7
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
20
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
What is inner alignment?
An explanation using the language of machine learning
 • 
Jan Leike
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
Musings on the Alignment Problem

Musings on the Alignment Problem

AboutArchiveRecommendationsSitemap
© 2023 Jan Leike
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing