In a test, researchers find that 90%+ of 1,008 jokes generated by GPT-3.5 were not new but rather the same 25 jokes likely learned during the model's training (Benj Edwards/Ars Technica) https://ift.tt/Nz2L9TF
Benj Edwards / Ars Technica : In a test, researchers find that 90%+ of 1,008 jokes generated by GPT-3.5 were not new but rather the same 25 jokes likely learned during the model's training — When tested, “Over 90% of 1,008 generated jokes were the same 25 jokes.” — On Wednesday, two German researchers …