Hacker News Reader

Comment by mtlynch | Hacker News Reader

I've never learned Haskell, so I'm maybe misunderstanding this, but it seems like this wouldn't cause problems for Copilot.

My understanding is that the author is effectively booby-trapping the entrypoints into their applications so that if someone runs the same code without the right "antidote" code extensions, it will go into an infinite loop. But that's only effective if Copilot picks up that one line with the booby trap. And Copilot probably wouldn't ever suggest that line because it's so different than the entrypoint to most Haskell applications.

View on HN

Indeed. And it wouldn't take much testing to realize the program is broken. This solution ignores the human in the loop at the controls of Copilot.

I wouldn't underestimate the coming arms race though, as developers find newer and more subtle poison pills to prevent rogue AIs from ingesting their code and regurgitating it later.

If someone is poisoning and obfuscating their own code base, they become the only person who can contribute to it, defeating the point of being FOSS and benefiting from community contributions and review.

This is being downvoted, but it touches on a really interesting phenomena we may eventually see, a sort of "arms race" where people try to make their code useless to machine learning, but simultaneously make it useless to people with lower skills (people blindly copying/pasting code with little understanding types).

As the machine learning becomes "smarter", this bar will raise, and more people will be coincidentally excluded in an attempt to keep unwanted algorithms from sucking up code.

Assuming this sort of poison-pill thing ever becomes commonplace.

... or just not open-source code any more. This is the silent, and much worse outcome.

nobody's got time to make obfuscated code rather than solve actual problems

The humans have been blindly copy-pasting from Stackoverflow for years, this simplifies that process. Especially for 10X remote engineers Copilot is a godsend.

On the contrary — this solution banks on the human in the loop growing frustrated at copilot’s inability to produce working code.

For that result to occur, you would need so much poisoned code that it became the dominant piece of the training data.

At that point, open source code becomes hard for humans to reason about. Very much cutting off one's nose despite one's face for the open source community.

> For that result to occur, you would need so much poisoned code that it became the dominant piece of the training data.

Hold my beer...

> My understanding is that the author is effectively booby-trapping the entrypoints into their applications

Not just. The linked example is booby-trapping a function.

Reply on news.ycombinator.com