Kevin Lu (@_kevinlu) 's Twitter Profile
Kevin Lu

@_kevinlu

@openai, working on synthetic data & reinforcement learning. ex-@berkeley_ai

ID: 1318713709175336960

linkhttp://kevinlu.ai calendar_today21-10-2020 00:40:35

33 Tweet

4,4K Takipçi

150 Takip Edilen

Kevin Lu (@_kevinlu) 's Twitter Profile Photo
Kevin Lu
@_kevinlu

2 months ago

So I think something else that doesn't get discussed much is the extrapolation of this inference : training trend - 2015: back in the day, we would train one model per dataset, and inference it once (to obtain the eval result for our paper) - 2020: with chatgpt, multi-task

So I think something else that doesn't get discussed much is the extrapolation of this inference : training trend - 2015: back in the day, we would train one model per dataset, and inference it once (to obtain the eval result for our paper) - 2020: with chatgpt, multi-task