News for hackers. Stuff that matters.
Re:GPT-4 by feoren on Tuesday March 14, 2023 @06:09PM (#35159700)
> In order to show lack of understanding you need to provide a clear test that ChatGPT would fail but a human would pass.

But that's literally what the top comment in this thread has just done. In fact there are dozens of examples in this HN comment section and thousands more readily Googlable online. It's very easy to clearly show that ChatGPT is a total bullshitter.

There are no comments on this comment yet.