[mstolpm]

Why are you discussing OpenAI with ChatGPT? I’m honestly interested.

I would imagine that any answer of ChatGPT on that topic is either (a) „hallucinated“ and not based on any verifiable fact or (b) scripted in by OpenAI.

The same question pops up for me whenever someone asks ChatGPT about the internals and workings of ChatGPT. Am I missing something?

[transcriptase]

Simple curiosity. I wanted to see if it could explain the shift in OpenAIs operating in a way that might give some interesting or perhaps novel insight (even if hallucinated) other than what their corpo-speak public facing reasoning is.

For the most part it just regurgitated the corpo-speak with an odd sense of confidence. I know that’s the point of the model, but it can also be surprisingly honest when it incorporates what it knows about human motivation and business.

[dopidopHN]

I’ve try because it’s tempting and the first attempts do give a « conversation » vibe.

I was curious about state persistence between prompt, or how to get my prompt better, or having a idea of the training data.

Only got crap and won’t spend time doing that again