I think they might even hang out when they’re outside the office…

This reminds me a little of “A Tale in the Desert”.

The AI seemed to struggle with scientific names for #19.

The question

was answered as no, though the correct answer should have been yes.

So if the answer is yes and no (conditional versus a universal property of the thing), you always answer yes? I would consider that strange, but as long as it is applied consistently then I suppose it is fine.

It is interesting, but with weird quirks.

It is definitely capable of responding with 🤷‍♂️, but neglects to do so in some expected areas.

“does it use a microprocessor?” 👍 “was it invented before 1970?” 👍

These are somewhat contradictory. No microwave in 1946-1971 could have had a microprocessor. If the answer is “sometimes yes, sometimes no” then 🤷‍♂️ is probably best.

In personally trying to use ChatGPT 4 for a job task (programming), I would disagree strongly with this sentiment. I have yet to find a task where it doesn’t partially fail due to no notion of the concepts underlying the topic.

In an example, I asked it to write an implementation of reading from a well known file type as a class. It had many correct ideas for certain operations (compiled from other sources of course), but failed with the basic concept of class instantiation. It was calling class methods in the constructor, which is just not allowed in the language being used. I went through several iterations with it to avail before just giving up on it.

In “normal” language tasks, it seems to be quirky, but passable. But if you give it a highly technical task where nuance and conceptual knowledge are needed? I have yet to see that work in any reliable capacity.

Oh that’s definitely true. I was just surprised to see something similar (especially the avoiding eye contact) in the animal kingdom.

“Contact” for a similar reason. It’s a mix of all motivations, along with people’s general mistrust of each other.