undefined | Better HN

0 pointsorbital-decay9mo ago0 comments

This is what mechanistic interpretability studies are trying to achieve, and it's not yet realistically possible for a general case.

0 comments

avarun9mo ago

Similarly to how you can never guarantee that one of your trusted employees won’t be made a foreign asset.

j / k navigate · click thread line to collapse

0 pointsorbital-decay9mo ago0 comments

This is what mechanistic interpretability studies are trying to achieve, and it's not yet realistically possible for a general case.

avarun9mo ago

Similarly to how you can never guarantee that one of your trusted employees won’t be made a foreign asset.

j / k navigate · click thread line to collapse