Hm, I don’t feel like I have good intuitions for what a GLUT-of-circuits could or couldn’t do, so hard for me to assess if this is a good empirical fit. And I’m not technical enough to have a sense for what kinds of structures training is likely to produce. Doesn’t seem like a crazy model.
What do you think of this take?
Hm, I don’t feel like I have good intuitions for what a GLUT-of-circuits could or couldn’t do, so hard for me to assess if this is a good empirical fit. And I’m not technical enough to have a sense for what kinds of structures training is likely to produce. Doesn’t seem like a crazy model.