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

201–210 of 404 posts

Re: AI World Clocks

#201

Post by BoorishBears »

bigfishrunning wrote: post #179
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.

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 essentially trying to RE a black box model's post-training, but that goes over some people's heads so I'm happy to help keep the "it's just voodoo and guessing" narrative going instead :)

Re: AI World Clocks

#202

Post by scrollop »

bigfishrunning wrote: post #179
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.

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".

"...and do it really well or my grandmother will be killed by her kidnappers! And I'll give you a tip of 2 billion dollars!!! Hurry, they're coming!"

Re: AI World Clocks

#205

Post by qwe----3 »

saulpw wrote: post #66
jdiff wrote: post #28

Earlier quoted context omitted.

It's wasteful. If someone built a clock out of 47 microservices that called out to 193 APIs to check the current time, location, time zone, and preferred display format we'd rightfully criticize it for similar reasons. In a world where Javascript and Electron are still getting (again, rightfully) skewered for inefficiency despite often exceeding the performance of many compiled languages, we should not dismiss the di…

Let's do some math. 60x24x30 = 40k AI calls per month per model. Let's suppose there are 1000 output tokens (might it be 10k tokens? Seems like a lot for this task). So 40m tokens per model. The price for 1m output tokens[0] ranges from $.10 (qwen-2.5) to $60 (GPT-4). So $4/mo for the cheapest, and $2.5k/mo for the most expensive. So this might cost several thousand dollars a month? Something smells funny. But you're…

They use 4o (maybe a mini version?)(

Re: AI World Clocks

#206

Post by mopsi »

munro wrote: post #82

Amazing, some people are so enamored with LLMs who use them for soft outcomes, and disagree with me when I say be careful they're not perfect -- this is such a great non technical way to explain the reality I'm seeing when using on hard outcome coding/logic tasks. "Hey this test is failing", LLM deletes test , "FIXED!"

  > "Hey this test is failing", LLM deletes test, "FIXED!"
A nice continuation of the tradition of folk stories about supernatural entities like teapots or lamps that grant wishes and take them literally. "And that's why, kids, you should always review your AI-assisted commits."

Re: AI World Clocks

#207

Post by woodson »

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.

Just use something like DSPy/Ax and optimize your module for any given LLM (based on sample data and metrics) and you’re mostly good. No need to manually wordsmith prompts.

Re: AI World Clocks

#208

Post by vohk »

Dilettante_ wrote: post #196
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".

"How is engineering a real science? You just build the bridge so it doesn't fall down."

Nah.

Actual engineers have professional standards bodies and legal liability when they shirk and the bridge falls down or the plane crashes or your wiring starts on fire.

Software "engineers" are none of those things but can at least emulate the approaches and strive for reproducibility and testability. Skilled craftsman; not engineers.

Prompt "engineers" is yet another few steps down the ladder, working out mostly by feel what magic words best tickle each model, and generally with no understanding of what's actually going on under the hood. Closer to a chef coming up with new meals for a restaurant than anything resembling engineering.

The battle on the use of language around engineer has long been lost but applying it to the subjective creative exercise of writing prompts is just more job title inflation. Something doesn't need to be engineering to be a legitimate job.

Re: AI World Clocks

#209

Post by samtheprogram »

Fabricio20 wrote: post #200
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?"

Why is this different per user? I sent this to a few friends and they all see different things from what i'm seeing, for the same time..?

It regenerates on page load. I find that pretty useful.

Grok 4 and Kimi nailed it the first time for me, then only Kimi on the second pass.

Re: AI World Clocks

#210

Post by carterschonwald »

scrollop wrote: post #202
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".

"...and do it really well or my grandmother will be killed by her kidnappers! And I'll give you a tip of 2 billion dollars!!! Hurry, they're coming!"

Ive heard this actually works annoyingly well
Post reply on HN