Re:Adventures with Compression
by moritzwarhier on Monday January 01, 2024 @03:51PM
(#38835220)
> On the other hand, LLMs expose the flaw in the Hutter prize
I'm not sure why it would be a flaw — isn't this more a sign of how universally interestint the rules are?
Out of curiosity, I didn't dive deeply into the previous winner's implementation, but are there NNs (+ error correction matrix, that's why I mentioned the FAQ in other comment) among them?
I'm not sure why it would be a flaw — isn't this more a sign of how universally interestint the rules are?
Out of curiosity, I didn't dive deeply into the previous winner's implementation, but are there NNs (+ error correction matrix, that's why I mentioned the FAQ in other comment) among them?