@mattsheffield@mastodon.social
2026-10-07 09:03 UTC
The main problem with claiming there are "pain," "sadness," etc. vectors is that these are human constructs for math matrices, not objective identifications.
What they really are is control methods. A car steering wheel does not literally steer the car. The steering rods do.
Replies (1)
-
@mattsheffield@mastodon.social 2026-10-07 09:03
The other problem is that the independent research shows quite clearly that what people are calling "circuits" or "features" for a concept are not unique at all. There are many possible activations for particular outputs. As one paper put it: All circuits lead to Rome: https://arxiv.org/html/2605.12671v1