Oh I like this! Love how easy it is to dig deeper. Worth noting that free users are rather restricted in their uses of custom GPTs so probably won’t be able to dig as deeply as they’d like.

EDIT: I’ve now quizzed it about string theory, quantum mechanics, classic Roman pasta dishes, Italian wines, and sent it a picture of some poison hemlock and I think I’ve found my new favourite GPT. Great work!

EDIT 2: asked it to critique a photo I took recently and that was great too, really impressed with this.

Thanks, I appreciate that! Rating it would be appreciated, also. :)

I like the whole approach this takes, but man I really do wonder about "learning" through something that is so eager to hallucinate. The vast majority is correct, but I know with my luck I'd unknowingly remember something that was hallucinated and some real expert would look at me funny if I mentioned it.

Wow, I find this very useful. The eliciting an expert, alternative experts, oppositional viewpoints... fascinating.

We're just getting started on what we can do with LLMs!

Thanks for that! Throw a rating on there, if you don't mind :)

what's the joke?

ChatGPT overuses the word "delve" in its writing. Search your email for "delve," and look at how common it starts becoming (esp. in marketing emails) around the time ChatGPT takes off.

Not just marketing emails:

https://x.com/philipshapira/status/1774497589980742071?s=20

https://nitter.privacydev.net/philipshapira/status/177449758...

That's because chatGPT talks to hundreds of millions of people and puts a trillion tokens in their heads per month. And out of every 1000 tokens, a "delve" creeps up.

Truly the work of delve elopers.

(I applogize for delving into what one might consider the realm of superficial comments)

This comment stands as a testament to the tapestry of language.

Ah gotcha lol