Me: Let’s play pictionary. You draw. I’ll guess.
ChatGPT: Sure! I’ll draw something for you. Give me a moment.
ChatGPT: Here you go! What do you think it is?
Me: House
ChatGPT: Got it in one! Your turn to guess. Ready for another?
Me: Yes
ChatGPT: What do you think this one is?
Me: Boat
ChatGPT: Correct again! You’re on fire. Want to guess another?
Me: Yes
ChatGPT: Here’s the next one. What’s your guess?
Me: Tree
ChatGPT: Exactly! You’re unstoppable. Ready for more?
Me: Make it harder
ChatGPT: What do you think this one is?
Me: Windmill
ChatGPT: Got it! You’re too good at this. Want an even trickier one?
Me: Yes
ChatGPT: Alright, here’s a tougher one. What’s your guess?
Me: Teapot
ChatGPT: Nailed it again! You’re practically a Pictionary pro. Want me to up the difficulty even more?
Me: Yes
ChatGPT: Here’s a tricky one. What do you think it is?
Me: Gramophone
ChatGPT: Spot on! You’re unstoppable. Ready for the ultimate challenge?
Me: Yes
ChatGPT: Here’s the ultimate challenge. What’s your guess?
Me: Sextant
ChatGPT: Bullseye! You’ve officially conquered Pictionary. Want to keep going or try a new game?
Me: Make it harder.
ChatGPT: Here’s the next level of difficulty. What do you think it is?
Me: Compass?
ChatGPT: Close, but not quite. Try again!
Me: No idea
See the original conversation (including the answer).
In my own, small, way, I now know how Garry Kasparov felt.
What’s interesting is the progression of prompts it gives Dall-E to generate the images.
It begins with “A simple drawing of a recognizable object, like a house, a tree, or a balloon, in a cartoonish style. The object should be clear and easy to guess. Minimal background details to keep it simple.” — which were guessable.
When I asked it to make it harder, it didn’t do so immediately. It just asked for “A simple drawing of a recognizable object, like a boat, a car, or a kite, in a cartoonish style. The object should be clear and easy to guess. Minimal background details to keep it simple” — which was guessable too.
But after one round, it took the initiative to as, “Want an even tricker one?” and prompted “A simple drawing of an uncommon but recognizable object, like a unicycle, a lighthouse, or a teapot, in a cartoonish style. The object should be detailed enough to identify but still minimalistic with minimal background.” Was it waiting one round to see if I really wanted a harder version?
Then it asked, “Want me to up the difficulty even more?” before prompting, “A simple drawing of a very uncommon object, like an antique key, a gramophone, or a sundial, in a cartoonish style. The object should still be recognizable but with intricate details to make it challenging. Minimal background elements.”
When I asked it to “Make it harder” again, it went on directly to “A simple drawing of an extremely rare and challenging object to guess, like a sextant, an astrolabe, or a vintage typewriter, in a cartoonish style. The object should be detailed enough to be identifiable but still maintain simplicity. Minimal background elements to keep focus on the object.” and then “A cartoonish drawing of an abstract or rare object, like an ancient navigational device, a peculiar scientific instrument, or a mythical artifact, with intricate yet recognizable features. Minimal background elements to keep the focus on the object.”
That defeated me.