Reply to ChatGPT is disappointingly stupid

Forum Index » Off-Topic

Reply to "ChatGPT is disappointingly stupid"

Subject:

Emoticons





More smilies

Text Color: Font: Close Marks

[quote=Anonymous][quote=Anonymous][quote=Anonymous][quote=Anonymous]You have to learn how to write prompts correctly. Seriously. Take a course in how to do it. You must also ask it to check it's work. Learn how to set the temps on hallucination. You have to put in some effort.[/quote]

I literally work in the field and this is wrong. [/quote]

Ok, expert. Correct me! What about the response is wrong?[/quote]

I will be very simplistic here but the full answer is more complex. Essentially, however, hallucinations aren’t a side effect. They are part and parcel of how foundation models work. At their base level, foundation models are doing token prediction. Hallucinations are the models working as intended.

For a long time, the hope was that accurate prompting could reduce hallucination incidence. That’s not turned out to be true, however, and you’ll notice that the major generative AI companies have stopped talking much about prompt engineering and are moving instead to focus on agentic querying. That’s because the next great hope is that agentic interfaces can catch hallucinations more efficiently. I’m personally skeptical but the field is moving quickly and it might work.

Prompt engineering can help around the edges, but it doesn’t reduce hallucinations particularly well. Neither does asking most foundation models to check their work, because that’s not how their token prediction works. [/quote]

Options

	Disable HTML in this message
	Disable BB Code in this message
	Disable smilies in this message

Review message

Search Recent Topics Hottest Topics