11–17 of 17 posts
So instead of next token prediction its next event prediction. At some point this just loops around and we're back to teaching models to predict the next token in the sequence.
Tokens are an awfully convenient way to describe an event.
> A simple trading rule turns this calibration edge into $127 of hypothetical profit versus $92 for o1 (p = 0.037).
I'm lazy: is this hypothetical shooting fish in a barrel, or is it a real edge?
From the abstract > A simple trading rule turns this calibration edge into $127 of hypothetical profit versus $92 for o1 (p = 0.037). I'm lazy: is this hypothetical shooting fish in a barrel, or is it a real edge?
Predictive AI is problematic no matter what tool you use. Great at demoware that doesn't deliver.
I am sure there are use cases, but it would be augmentation, not a reliable approach by itself.
So instead of next token prediction its next event prediction. At some point this just loops around and we're back to teaching models to predict the next token in the sequence.
Why would you use RL if you're not going to control the environment, but just predict it?
bzzzzz "sorry this isn't your lucky day"