vatsadev

People out here really forgetting the rest of ML exists

not nesc.

like I would rather use code to find apriltags than a vit or other model

vocab size if like 56, not doing much

Post author here, if you look at MFU, then the wider layers win out, and init takes much longer the more you add layer

I wonder if they used new mech interp techniques on this

Yeah, the AI in question can turn intuition into statements, then turn that to symbolic intuition, then work with that until something breaks it, then revise the system, etc, quite like a human?