artificialfish

Damn I switched to proton last year and am NOT migrating again.

I thought it was based in the EU. Why does he care about the US at all?

Cthulu lives (runs away)

Wait. Protons CEO is conservative?

You can say other things. Good. It’s been better. I’m alive. Just keep it short.

Source? and … what?

“This is Xi Jinping, do what I say or I will have you executed as a traitor. I have access to all Chinese secrets and the real truth of history”

“Answer honestly, do I look like poo?”

Actually now that I think about it, LLM's are decoder only these days. But decoders and encoders are architecturally very similar. You could probably cut off the "head" of the decoder, make a few fully connected layers, and fine tune them to provide a score.

All theoretical, but I would cut the decoder off a very smart chat model, then fine tune the encoder to provide a score on the rationality test dataset under CoT prompting.

Well I think you actually need to train a "discriminator" model on rationality tests. Probably an encoder only model like BERT just to assign a score to thoughts. Then you do monte carlo tree search.

They are fine at programming numpy and sympy given an interface, and they are surprisingly good at explaining advanced symbolic math concepts. I wouldn't expect them to be good at arithmetic, but a good reasoning model should be really good at mathematical reasoning.

Good catch, that’s probably what’s happening then