Hacker News new | past | comments | ask | show | jobs | submit login

Yes - the default model really needs to be trained with an opensource optimizer on a corpus of open source code (ie. with a license at least as permissive as llvm itself).

A blob trained with proprietary google tech on a proprietary google codebase isn't opensource. Even if it were, Google C++ differs in style quite widely from typical C++, so the model probably isn't as good as a model trained on all of github.




Someone created a github issue for this: https://github.com/llvm/llvm-project/issues/56432




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

Search: