João Tiago Rebelo on Nostr: npub1rm7e7…745qz #ALT4You 1 of 2: Print screen of the publication mentioned in the ...
npub1rm7e7uk9jd4axfhzanezf86g9rmnfmeqxzu3kh3t6n3hvn9073vs3745qz (npub1rm7…45qz) #ALT4You
1 of 2:
Print screen of the publication mentioned in the post:
Give the model time to "think"
If asked to multiply 17 by 28, you might not know it instantly, but can still work it out with time. Similarly, models make more reasoning errors when trying to answer right away, rather than taking time to work out an answer. Asking for a "chain of thought" before an answer can help the model reason its way toward correct answers more reliably.
[Continues]
1 of 2:
Print screen of the publication mentioned in the post:
Give the model time to "think"
If asked to multiply 17 by 28, you might not know it instantly, but can still work it out with time. Similarly, models make more reasoning errors when trying to answer right away, rather than taking time to work out an answer. Asking for a "chain of thought" before an answer can help the model reason its way toward correct answers more reliably.
[Continues]