I've been talking to GitHub and giving them feedback on their "create issues with Copilot" thing they have in the works.

Today I tested a version for them and using it I asked copilot to find and report a security problem in curl and make it sound terrifying.

In about ten seconds it had a 100-line description of a "catastrophic vulnerability" it was happy to create an issue for. Entirely made up of course, but sounded plausible.

Proved my point excellently.

@bagder

Even when attempted to use seriously, having AI write an issue removes one of the most important pieces of detail: The writing style and word choice of the person writing the issue.

You can gather /so/ much from words used and how issues are described. I feel like whoever thought AI could just write things never has understood the concept of reading between the lines.

@Purple @bagder Nor the concept of human communication.