training

I trained a small transformer from scratch in 1.5hrs on a 5090
Beats many LLMs, and scores the same as TRM/HRM

If you put all these things together:- RLHF = training the model to be likable by humans- RLVR = training the model to be accepted by machines- RLVR is more scalable- "Alignment tax" says "likable by humans" makes the model do worse on verifiable tasks

If this continues, there’s a world where 3rd party harnesses become less valuable when used with frontier lab models because the 1st party harness behavior is already baked in. And there’s no longer a fine tuning escape hatch to generalize this behavior away.

The conclusion I draw is that empathy in these systems is not an inherent state but a manufactured quantity.