Welcome to Programmer Humor!
This is a place where you can post jokes, memes, humor, etc. related to programming!
For sharing awful code theres also Programming Horror.
I got a couple of good ones:
When I first opened it, deepseek also had a correct clock, but I accidentally refreshed the page when I scrolled up to double check its time, second time through only these two were right
Ed. Names are below the clock, the top one was by the clock drawing champion Kimi K2
Is it just me or the clocks frequently break or change appearance without the page being refreshed?
Edit: nevermind, I skipped past the sentence explaining that every minute, the site prompts LLMs for a new solution. This is hilariously sad how LLMs aren't able to be consistent from one prompt to another.
It's the expected result if your big ol' artificial intelligence wannabe is ultimately just a stochastic word combinator.
if every single token is, at the end, chosen by random dice roll (and they are) then this is exactly what you'd expect.
Some of these are absolutely hilarious
Another reason why, while AI might be a fun toy, no one who is serious about getting work done will touch it with a dirty barge pole. The gratuitous hallucinations alone ought to be a sufficient deterrent.
The last one, Kimi K2, has been consistently good as long as I've been looking at it. That's pretty impressive.
The rest are hilarious!
Deepseek has a recognisable clock now and then, too. They both mix up the current time, though.
By far the best, but still off. These three were loaded in the same order as i post them:
I dig the square clock, and am now sad that the numbers can't be put into the corners on a real clock. Unless they're shifted from the usual position.
Cartier found a work around quite some time ago and maybe they weren't even the first to design a square 'clock':
(The roman numerals are nice, but notice the 'circle' between the numerals and the hands, almost like the circle from the ai)
That one is pretty good, though the Roman numerals are rather busy and uneven.
This one is closer, though now I have to wonder if all non-square rectangular clocks have an old-timey whiff for me, or it's just the border here:
This is also impressive:
I like the second one a lot, especially how the upper and bottom numerals face the floor and the left and right ones face towards the center, and to allow for that there has to be a sudden flip from 3>4 and 8>9. But the indices are not playing by the square-clock rule and unlike the cartier one form a regular oval shape.
I like how the upper one had to find a way to make clear which indice represents the numerals - it really shows the problem in projecting the circular movement of the hands into a rectangular (thanks, that's the right word) shape.
It think most analog clocks/watches will give you an old-timey whiff much more often than not, just because there is a more new-timey alternative. I went looking for some watch faces for smart watches, but couldn't really find any interesting one. Most are either digital numbers or a round clock on a rectangular display.
Neither of those interest me like the Cartier tank, which I find really ugly watches to be honest. It's just this double outlined rectangle(-ish shape) which is unevenly split into 60 boxes that I like (seen below on the first, third and fifth watch).
Haha, I found myself thinking the same thing, and then caught myself, realizing all the other LLMs on this page had lowered the bar immensely for what I'm considering impressive.
I thought the same and then Kimi K2 came up with a clock that has two 12 and no 11...
I don't even
I was surprised that both Grok and Gemini 2.5 got it right once, only to fuck it up on the refresh
qwen 2.5 is absolutely pants on head ridiculous compared to gpt5 when I'm looking at it right now.
Given that the AI models are basically constructing these "blindly"- using the language model to string together html and javascript without really being able to check how it looks- some of these are actually pretty impressive. But also making the AI do things it's bad at is funny. Reminds me of all the AI ASCII art fails...
qwen is trying her best 😭😔
So far, I’d give qwen the prize for most artistic impression of a clock.
Kimi K2 appears to consistently get it right.
What is this obsession with clocks recently?
I don't know if it's actually related, but I've read that asking people to draw a clock face is a simple way to identify some brain problems
Quick screening for dementia, according to this
Edit: I guess this means most of the AI has 'Conceptual Deficits', pretty accurate lol
Would be funny if AI models are generating such wildly useless "clocks" because they ingested too many dementia screening tests in their training data
There is someone training the biggest, bestest model to draw clock faces to pass that test as we speak.
I'm guessing it's an easy metric to compare benchmarks. "Write a clock".
Well, KIMI K2 seems to have created the working one. Others failed. I suppose that this model was optimized for this while others not.
The clocks change every minute. I've seen some from deepseek and qwen that looked ok. But kimi seems to be the most consistent
Not really world clocks, they just try to use JavaScript to display the device's time.
No JavaScript I think, it's just html and CSS. The initial time is provided in the prompt every minute according to the description. I wonder if they'd be any better if they could use js. Probably not.
Really cool idea, but the site seems a bit biased for the chinese models, or is otherwise set up weird. I’m not able to reproduce how consistently bad the others are in web dev arena, which generally accepted as the gold standard for testing AI web dev ability.
Each model is allowed 2000 tokens to generate its clock. Here is its prompt: Create HTML/CSS of an analog clock showing ${time}. Include numbers (or numerals) if you wish, and have a CSS animated second hand. Make it responsive and use a white background. Return ONLY the HTML/CSS code with no markdown formatting.
are you using the same prompt?
You know, I don't, and what the fuck?
Deepseek seems to have the only functional clock.
Depends on when you load it. They refresh every minute. In the first one I got, Deepseek's was almost functional, but Haiku had one that was surprisingly good.
I've never seen any of the OpenAI models come up with anything that was more than completely broken.
