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

171–180 of 404 posts

Re: AI World Clocks

#171

Post by pil0u »

porphyra wrote: post #156

LLMs can't "look" at the rendered HTML output to see if what they generated makes sense or not. But there ought to be a way to do that right? To let the model iterate until what it generates looks right. Currently, at work, I'm using Cursor for something that has an OpenGL visualization program. It's incredibly frustrating trying to describe bugs to the AI because it is completely blind. Like I just wanna tell it "th…

I had some success providing screenshots to Cursor directly. It worked well for web UIs as well as generated graphs in Python. It makes them a bit less blind, though I feel more iterations are required.

Re: AI World Clocks

#173

Post by paulddraper »

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.

Kimi K2 is legitimately good.

Re: AI World Clocks

#175

Post by stogot »

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.

When I clicked, everything was garbage except Grok and DeepSeek. kimi was the worst clock

Re: AI World Clocks

#176

Post by esafak »

phkahler wrote: post #90
echelon wrote: post #48

Earlier quoted context omitted.

gpt-image-1 and Google Imagen understand prompts, they just don't have training data to cover these use cases. gpt-image-1 and Imagen are wickedly smart. The new Nano Banana 2 that has been briefly teased around the internet can solve incredibly complicated differential equations on chalk boards with full proof of work.

>> The new Nano Banana 2 that has been briefly teased around the internet can solve incredibly complicated differential equations on chalk boards with full proof of work. That's great, but I bet it can't tie it's own shoes.

And a submarine can't swim. Big deal.

Re: AI World Clocks

#177

Post by cornonthecobra »

I like Deepseek v3.1's idea of radially-aligning each hour number's y-axis ("1" is rotated 30° from vertical, "2" at 60°, etc.). It would be even better if the numbers were rotated anticlockwise.

I'm not sure what Qwen 2.5 is doing, but I've seen similar in contemporary art galleries.

Re: AI World Clocks

#179

Post by bigfishrunning »

bArray wrote: post #104
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 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.

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".

Re: AI World Clocks

#180

Post by echelon »

phkahler wrote: post #90
echelon wrote: post #48

Earlier quoted context omitted.

gpt-image-1 and Google Imagen understand prompts, they just don't have training data to cover these use cases. gpt-image-1 and Imagen are wickedly smart. The new Nano Banana 2 that has been briefly teased around the internet can solve incredibly complicated differential equations on chalk boards with full proof of work.

>> The new Nano Banana 2 that has been briefly teased around the internet can solve incredibly complicated differential equations on chalk boards with full proof of work. That's great, but I bet it can't tie it's own shoes.

No, but I can get it to do a lot of work.

It's a part of my daily tool box.

Post reply on HN