MUCH less training for SLIGHTLY worse results. It's a huge benefit to be able to... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		freeone3000 on May 29, 2020 \| parent \| context \| favorite \| on: GPT-3: Language Models Are Few-Shot Learners MUCH less training for SLIGHTLY worse results. It's a huge benefit to be able to make this trade-off.

drusepth on May 29, 2020 [–]

Is the reverse also true? If you have the training data necessary for "good" results on GPT-2, is it generally correct to assume that it would provide better results on your task than GPT-3?

freeone3000 on May 30, 2020 | [–]

If you can answer this question without running both models over the data set, you've got a very good paper on your hands.

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact