Hacker News new | ask | show | jobs
by david2ndaccount 1265 days ago
When it works it’s impressive, but sometimes it just makes things up:

For one of my repos: https://github.com/drpriver/macwatch

> Does this program work on windows?

No, macwatch is a program designed specifically for Mac computers and is not compatible with Windows systems. The program is designed to provide users with a comprehensive overview of their Mac's performance, including CPU usage, memory usage, disk usage, and more. It can also be used to monitor network activity and alert users when a process is consuming too much system resources. Additionally, the code provided is written in Objective-C and C, which are not supported on Windows systems.

---

The first sentence is correct, the rest is just completely wrong.

2 comments

This is in general problem with gpt models.

When it works, it’s flawless. When it doesn’t work, it just makes stuff up that kind of look good, just to make you happy. And there is really no way to tell from the output…

Pretty funny how it seems to just have invented something based on nothing more than the name macwatch. The last sentence is remarkably strange, like it's just riffing on the idea of "not supported on Windows" and decided to throw in some random facts about the repo, and wound up with a totally false statement.