Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI World Clocks

clocks.brianmoore.com

Post reply on HN
Print view View original

261–270 of 404 posts

Re: AI World Clocks

#261

Post by lanstin »

BoorishBears wrote: post #201
bigfishrunning wrote: post #179

Earlier quoted context omitted.

How much engineering do prompt engineers do? Is it engineering when you add "photorealistic. correct number of fingers and teeth. High quality." to the end of a prompt? we should call them "prompt witch doctors" or maybe "prompt alchemists".

I like that actually, I've spent the last year probably 60:40 between post-training and prompt engineering/witch doctoring (the two go together more than most people realize) Some of it is engineering-like, but I've also picked up a sixth sense when modifying prompts about what parts are affecting the behavior I want to modify for certain models, and that feels very witch doctory! The more engineering-like part is es…

I think the coherence behind prompt engineering is not in the literal meanings of the words but finding the vocabulary used by the sources that have your solution. Ask questions like a high school math student and you get elementary words back. Ask questions in the lingo of a Linux bigot and you will get good awk scripts back. Use academic maths language and arXiv answers will be produced.

Re: AI World Clocks

#262

Post by nightpool »

bspammer wrote: post #225
lanewinfield wrote: post #94

hi, I made this. thank you for posting. I love clocks and I love finding the edges of what any given technology is capable of. I've watched this for many hours and Kimi frequently gets the most accurate clock but also the least variation and is most boring. Qwen is often times the most insane and makes me laugh. Which one is "better?"

If you're keeping all the generated clocks in a database, I'd love to see a Facemash style spin-off website where users pick the best clock between two options, with a leaderboard. I want to know what the best clock Qwen ever made was!

Yes! Please do this

Re: AI World Clocks

#263

Post by nightpool »

otterley wrote: post #89

Watching this over the past few minutes, it looks like Kimi K2 generates the best clock face most consistently. I'd never heard of that model before today! Qwen 2.5's clocks, on the other hand, look like they never make it out of the womb.

It would be cool to also AI generate the favicon using some sort of image model.

Re: AI World Clocks

#264

Post by ceroxylon »

hakcermani wrote: post #260
lanewinfield wrote: post #94

hi, I made this. thank you for posting. I love clocks and I love finding the edges of what any given technology is capable of. I've watched this for many hours and Kimi frequently gets the most accurate clock but also the least variation and is most boring. Qwen is often times the most insane and makes me laugh. Which one is "better?"

.. would you mind sharing the prompt .. in a gist perhaps .

They have it available on the site under the (?) button:

"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."

Re: AI World Clocks

#265

Post by ceroxylon »

andix wrote: post #231
bArray wrote: post #104

Earlier quoted context omitted.

It could be that the prompt is accidentally (or purposefully) more optimised for Kimi K2, or that Kimi K2 is better trained on this particular data. LLM's need "prompt engineers" for a reason to get the most out of a particular model.

I think the selection of models is a bit off. Haiku instead of Sonnet for example. Kimi K2's capabilities are closer to Sonnet than to Haiku. GPT-5 might be in the non-reasoning mode, which routes to a smaller model.

I had my suspicions about the GPT-5 routing as well. When I first looked at it, the clock was by far the best; after the minute went by and everything refreshed, the next three were some of the worst of the group. I was wondering if it just hit a lucky path in routing the first time.

Re: AI World Clocks

#266

Post by abixb »

bspammer wrote: post #225
lanewinfield wrote: post #94

hi, I made this. thank you for posting. I love clocks and I love finding the edges of what any given technology is capable of. I've watched this for many hours and Kimi frequently gets the most accurate clock but also the least variation and is most boring. Qwen is often times the most insane and makes me laugh. Which one is "better?"

If you're keeping all the generated clocks in a database, I'd love to see a Facemash style spin-off website where users pick the best clock between two options, with a leaderboard. I want to know what the best clock Qwen ever made was!

We might be on to creating a new crowd-ranked LLM benchmark here.

Re: AI World Clocks

#267

Post by smusamashah »

lanewinfield wrote: post #94

hi, I made this. thank you for posting. I love clocks and I love finding the edges of what any given technology is capable of. I've watched this for many hours and Kimi frequently gets the most accurate clock but also the least variation and is most boring. Qwen is often times the most insane and makes me laugh. Which one is "better?"

Please make it show last 5 (or some other number) of clocks for each model. It will be nice to see the deviation and variety for each model at a glance.

Re: AI World Clocks

#268

Post by chanux »

baltimore wrote: post #21

Since the first (good) image generation models became available, I've been trying to get them to generate an image of a clock with 13 instead of the usual 12 hour divisions. I have not been successful. Usually they will just replace the "12" with a "13" and/or mess up the clock face in some other way. I'd be interested if anyone else is successful. Share how you did it!

Ah! This is so sad. The manager types won't be able to add an hour (actually, two) to the day even with AI.

Re: AI World Clocks

#269

Post by userbinator »

andix wrote: post #236
baltimore wrote: post #21

Since the first (good) image generation models became available, I've been trying to get them to generate an image of a clock with 13 instead of the usual 12 hour divisions. I have not been successful. Usually they will just replace the "12" with a "13" and/or mess up the clock face in some other way. I'd be interested if anyone else is successful. Share how you did it!

I gave this "riddle" to various models: > The farmer and the goat are going to the river. They look into the sky and see three clouds shaped like: a wolf, a cabbage and a boat that can carry the farmer and one item. How can they safely cross the river? Most of them are just giving the result to the well known river crossing riddle. Some "feel" that something is off, but still have a hard time to figure out that wolf,…

Basically a variation of https://en.wikipedia.org/wiki/Age_of_the_captain

Re: AI World Clocks

#270

Post by Springtime »

anon_cow1111 wrote: post #241
perfmode wrote: post #232

Earlier quoted context omitted.

i read that the OP limited the output to 2000 tokens.

I got a ~1600 character reply from gpt, including spaces and it worked first shot dumping into an html doc. I think that probably fits ok in the limit? (If I missed something obvious feel free to tell me I'm an idiot)

On the second minute I had the AI World Clocks site open the GPT-5 generated version displayed a perfect clock. Its clock before and every clock from it since has had very apparent issues though.

If you could get a perfect clock several times for the identical prompt in fresh contexts with the same model then it'd be a better comparison. Potentially the ChatGPT site you're using though is doing some adjustments that the API fed version isn't.

Post reply on HN