Just fantastic technology all around. Absolutely no worry where this is all going to go.

Is it just me? Am I using this wrong or am I asking questions that are too hard?

Here’s an example of a hallucination that happened while explaining away another hallucination I called it out on. I rarely have experiences other than these.

@mwichary Aggressively specific prompting can help a bit, like: “Can you give me three specific examples of women who made significant accomplishments in interface design, human factors, or ergonomics work? I need you to check to make sure they really exist, and cite evidence of their excellence.” ChatGPT (free) gave me Susan Kare, Susan M. Dray, and S. Joy Mountford. Claude (free) gave Enid Mumford, Dray, and Lucy Suchman. Real, at least. But history research questions are not their strength.
@mwichary I find this kind of use case more interesting, essentially a way to get some editing suggestions when stuck on a draft or wanting a different perspective, although not as good as a real person (of course): https://www.techdirt.com/2024/04/29/how-i-use-ai-to-help-with-techdirt-and-no-its-not-writing-articles/
How I Use AI To Help With Techdirt (And, No, It’s Not Writing Articles)

Let’s start off this post by noting that I know that some people hate anything and everything having to do with generative AI and insist that there are no acceptable uses of it. If that describes y…

Techdirt
@brittag The last sentence might be key; I wonder if I want that disproportionately more often than others?