> The words that are coming out of the model are generated to optimize for RLHF and closeness to the training data, that's it! This is false, reasoning models are rewarded/punished based on performance at verifiable…
BT2 is old news, we have BT4 now
An excellent explanation of Magic Bitboards can be found here: https://analog-hors.github.io/site/magic-bitboards/
this pretty much summarises my opinion - one nitpick - i assume you meant "omit bounds and other checks", not "emit bounds and other checks" which seems to mean the opposite of what you're intending
> The words that are coming out of the model are generated to optimize for RLHF and closeness to the training data, that's it! This is false, reasoning models are rewarded/punished based on performance at verifiable…
BT2 is old news, we have BT4 now
An excellent explanation of Magic Bitboards can be found here: https://analog-hors.github.io/site/magic-bitboards/
this pretty much summarises my opinion - one nitpick - i assume you meant "omit bounds and other checks", not "emit bounds and other checks" which seems to mean the opposite of what you're intending