I asked GPT4 the same prompt and here is what it said:
Of course! Here's a new contra dance for you:
Contra Dance
Whirlwind Delight
By ChatGPT
(Duple improper)A1
(8) Circle left 3/4
(8) Neighbor swing
A2
(8) Long lines forward and back
(8) Ladies chain
B1
(8) Star right 1x
(8) Gents aleman left 1.5
B2
(8) Half hey, ladies pass right shoulders to start
(8) Partner balance and swing, end facing down in a line of four
Enjoy dancing Whirlwind Delight!
How did it do?
If we want to know what arguments resonate with New York Times articles we can actually use surveys, message testing, and focus groups to check and we don't need to guess! (Disclaimer: My company sells these services.)
That makes a lot of sense. We can definitely test a lot of different framings. I think the problem with a lot of these kinds of problems is that they are low saliency, and thus people tend not to have opinions already, and thus they tend to generate an opinion on the spot. We have a lot of experience polling on low saliency issues though because we've done a lot of polling on animal farming policy which has similar framing effects.
I'll shill here and say that Rethink Priorities is pretty good at running polls of the electorate if anyone wants to know what a representative sample of Americans think about a particular issue such as this one. No need to poll Uber drivers or Twitter when you can do the real thing!
Yeah, it came from a lawyer. The point being that if you confess to something bad, we may be legally required to repot that, so be careful.
This is a great poll and YouGov is a highly reputable pollster, but there is a significant caveat to note about the pause finding.
The way the question is framed provides information about "1000 technology leaders" who have signed a letter in favor of the pause but does not mention any opposition to the pause. I think this would push respondents to favor the pause. Ideal question construction would present more neutrally with both support and oppose statements.