x

LESSWRONG
LW

David Reber

David Reber

Message

I am a Ph.D. student in Computer Science at the University of Chicago, advised by Victor Veitch and Ari Holtzman. I’m developing ways to do precise causal inference over irreducibly subjective variables — the kind that matter for understanding LLMs but can’t be cleanly formalized....

131

2

24

5y

David Reber

I am a Ph.D. student in Computer Science at the University of Chicago, advised by Victor Veitch and Ari Holtzman. I’m developing ways to do precise causal inference over irreducibly subjective variables — the kind that matter for understanding LLMs but can’t be cleanly formalized....

David Reber — LessWrong

Your Causal Variables Are Irreducibly Subjective

Mechanistic interpretability needs its own shoe leather era. Reproducing the labeling process will matter more than reproducing the Github. Crossposted from Communication & Intelligence substack When we try to understand large language models, we like to invoke causality. And who can blame us? Causal inference comes with an impressive toolkit:...

Using Finite Factored Sets for Causal Representation Learning?

One of the primary motivations of Finite Factored Sets (shorthand: FFS) that initially caught my eye was, to quote Scott: > "Given a collection of variables and a joint probability distribution over those variables, Pearl can infer causal/temporal relationships between the variables.", the words "Given a collection of variables" are...

Jan 11, 2023•2