Why would you consider this a good prompt?

minimaxir 2 hours ago | parent | next [-]

Because both Nano Banana Pro and ChatGPT Images 2.0 have touted strong reasoning capabilities, and this particular prompt has more objective, easy-to-validate criteria as opposed to the subjective nature of images.

I have more subjective prompts to test reasoning but they're your-mileage-may-vary (however, gpt-2-image has surprisingly been doing much better on more objective criteria in my test cases)

▲

o10449366 an hour ago | parent | prev [-]

Because it's quirky and obscure.

HNers love to write prompts that "prove" they're still smarter than AI.

These are likely the same people that ask ridiculous coding questions in interviews to dunk on candidates even if the questions are totally unrelated to the job.

	▲	minimaxir an hour ago \| parent \| next [-]
		"Quirky and obscure" has the functional benefit of ensuring the source question is not in the training data/outside the median user prompt, and therefore making the model less likely to cheat. We have enough people complaining about Simon Willison's pelican test.
	▲	Bjartr 11 minutes ago \| parent \| prev \| next [-]
		What would make the prompt a better actual evaluation in your judgement?
	▲	tailscaler2026 25 minutes ago \| parent \| prev \| next [-]
		still #opentowork huh
	▲	codemog an hour ago \| parent \| prev [-]
		Ah yes, also known as C++ enjoyers.