Hacker News new | past | comments | ask | show | jobs | submit login
AI Coding with CodeRL: Toward Mastering Program Synthesis with Deep RL (salesforceairesearch.com)
1 point by moyix on July 21, 2022 | hide | past | favorite | 1 comment



The TL;DR is that this appears to beat both OpenAI Codex (12 billion params) and DeepMind's AlphaCode (1 billion params), despite having only 770M parameters.

There is also a paper: https://arxiv.org/abs/2207.01780

And the code is available: https://github.com/salesforce/CodeRL




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

Search: