[lemmsjid]

I noticed he mentioned asking Bing, so I directly asked ChatGPT “who is Ryan McGreal?” and it wrote, “ Ryan McGreal is a writer, urbanist, and the editor of Raise the Hammer, an online publication that focuses on urban issues, transportation, and sustainability. He has been actively involved in advocating for better urban planning and transportation policies in Hamilton, Ontario, Canada. Please note that my knowledge is based on information available up to September 2021, so there may have been developments or changes in his work or activities since then.”

That appears more or less correct

So to give chatgpt an opportunity to hallucinate similarly to the article, I followed up with, “Did he write for the nyt?” and it replied, “ I do not have any information indicating that Ryan McGreal has written for The New York Times (NYT). His work primarily focuses on urban issues and transportation, as mentioned earlier, and he is associated with Raise the Hammer, a local publication in Hamilton, Ontario, Canada. It’s possible that he may have contributed to other publications, but I do not have specific information regarding his contributions to The New York Times.”

While I have seen ChatGPT make stuff up I do think it’s useful to compare specific results across LLMs before using particular examples to make holistic statements.

[j16sdiz]

Try it in other way: Ask something big (with lots of text, in this case: NYT) first .

Ask in this order:

1) what is NYT (New York times)?

2) Who is Ryan McGreal?

3) Did he wrote for NYT?

This build up more context for hallucinating