Highest score is 16,800.
Highest streak is 60 in a row.
I just came to HN to see if I won!
Also, I do research on how people perceive images and video. I’ve published a couple papers and did my dissertation on how folks understand moving images.
If you’re the developers of this game I’d love to help you parse this data. B L T P H D at V T dot E D U.
Something we’ve been discussing in our lab is if people can detect the “taste” of AI. Seems if you play this game enough times, you can at least recognize the differences pretty consistently. I’d love to know how rounds of play improves people’s accuracy.
Next time you eat at McDonald’s try to notice the similarities in how things taste. McDonald’s has a flavor profile across all their foods. Everything is a little sweeter and a little saltier but exactly “McDonald’s-like.” My favorite example is the sauces for chicken nuggets. Regardless of the flavor you get, all the sauces have the same consistency and sort of taste like sweet and sour sauce. The honey mustard, the bbq, the buffalo sauce, and even the ranch all taste McDonaldish.
My working theory is that AI generated content also has a tatse. Once you can taste it, you are able to easily discern genuine content (which has random tastes) from generated content (which taste like the model it comes from).
SoylentGreenGPT · · focus · HN ↗
I just came to HN to see if I won!
Also, I do research on how people perceive images and video. I’ve published a couple papers and did my dissertation on how folks understand moving images.
If you’re the developers of this game I’d love to help you parse this data. B L T P H D at V T dot E D U.
Something we’ve been discussing in our lab is if people can detect the “taste” of AI. Seems if you play this game enough times, you can at least recognize the differences pretty consistently. I’d love to know how rounds of play improves people’s accuracy.
SoylentGreenGPT · · focus · HN ↗
My working theory is that AI generated content also has a tatse. Once you can taste it, you are able to easily discern genuine content (which has random tastes) from generated content (which taste like the model it comes from).