Re:GitHub Copilot available for JetBrains and Neovim
by ctoth on Wednesday October 27, 2021 @05:07PM
(#29019150)
I don't know if this is true, but I would assume that the tokenizers they used for Codex use actual language parsers which would drop invalid files like this and make this attack infeasible.
When I was playing around a couple years ago with the Fastai courses in language modeling I used the Python tokenize module to feed my model, and with excellent parser libraries like Lark[0] out there it wouldn't take that long to build real quality parsers.
Of course I could be totally wrong and they might just be dumping pure text in, shutter.
When I was playing around a couple years ago with the Fastai courses in language modeling I used the Python tokenize module to feed my model, and with excellent parser libraries like Lark[0] out there it wouldn't take that long to build real quality parsers.
Of course I could be totally wrong and they might just be dumping pure text in, shutter.
[0]: https://github.com/lark-parser/lark