GPT-3: A Summary

post by leogao · 2020-06-02T18:14:54.380Z · LW · GW · 0 comments

This is a link post for https://leogao.dev/2020/05/29/GPT-3-A-Brief-Summary/

With massive size comes massive generalization ability: GPT-3 is competitive in many benchmarks without even tuning on the target task. [...] Perhaps the most impressive part, though, is that even at such a massive scale, the model still scales smoothly in performance instead of plateauing, implying that still-larger models would perform even better.

0 comments

Comments sorted by top scores.