Hacker News new | ask | show | jobs
by wavemode 99 days ago
We're definitely not at that point.

If this blog post is unedited LLM output, the blog owner needs to sell whatever model, setup and/or prompt he used for a million dollars, since it's clearly far beyond the state-of-the-art in terms of natural-sounding tone.

1 comments

You can make an LLM sound very natural if you simply ask for it and provide enough text in the tone you’d like it to reproduce. Otherwise, it’s obvious that an LLM with no additional context will try to stick to the tone the company aligned it to produce
”I named it Cutlet after my cat. It’s completely legal to do that.”

I’ve never seen LLM being able to produce these kind of absurdist jokes. Or any jokes, really.

comedy is a completely different thing than natural tone. I agree that they’re incapable of coming up with decent jokes
Agree. I keep asking LLMs to tell me some jokes from time to time, but never once I've found it's funny. For me, when I find myself burst out laughing from LLMs joke, I'd know we've reached AGI.
You doing it wrong way - you should not ask for jokes - you need to structure prompt so jokes are byproduct.
here - an AI generated dadjoke:

Why did the cabbage refuse to testify in court? It didn't want to be grilled and then shredded.

Seems to be knew and very corny.

I never claimed that you can't get natural tone out of an LLM. What I said was that you can't get this blog post out of one.

By all means, go read the post and then try to do so.