Just out of curiosity, in what sense is Codex is better trained than CodeGen? | Hacker News

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

		obastani on Dec 23, 2022 \| parent \| context \| favorite \| on: SantaCoder: A new 1.1B code model for generation a... Just out of curiosity, in what sense is Codex is better trained than CodeGen?

moyix on Dec 23, 2022 [–]

OpenAI hasn't said exactly how they trained code-davinci-002 so this is speculative, but I'm reasonably sure it was trained on more data and languages than CodeGen and for longer. It was also trained using fill-in-the middle [1].

[1] https://arxiv.org/abs/2207.14255

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact