LESSWRONG
LW

Interpretability (ML & AI)AIWorld Modeling
Frontpage

3

A day in the life of a mechanistic interpretability researcher

by Bill Benzon
28th Nov 2023
1 min read
3

3

Interpretability (ML & AI)AIWorld Modeling
Frontpage

3

A day in the life of a mechanistic interpretability researcher
3Ben Pace
1Joyee Chen
3Bill Benzon
New Comment
3 comments, sorted by
top scoring
Click to highlight new comments since: Today at 2:56 AM
[-]Ben Pace2y31

That was fun to watch. But I would appreciate someone spelling out the implied connection to mechanistic interpretability.

Reply
[-]Joyee Chen2y10

Hint: does Charlie Chaplin have a gears-level understanding of the system?

Reply
[-]Bill Benzon2y30

LOL! Plus he's clearly lost in a vast system he can't comprehend. How do you comprehend a complex network of billions upon billions of weights? Is there any way you can get on top of the system to observe its operations, to map them out?

Reply
Moderation Log
More from Bill Benzon
View more
Curated and popular this week
3Comments