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

Ask HN: Share your AI prompt that stumps every model

news.ycombinator.com

Post reply on HN
Print view View original

141–150 of 670 posts

Re: Ask HN: Share your AI prompt that stumps every model

#141

Post by echoangle »

alganet wrote: post #102
miki123211 wrote: post #94

No, please don't. I think it's good to keep a few personal prompts in reserve, to use as benchmarks for how good new models are. Mainstream benchmarks have too high a risk of leaking into training corpora or of being gamed. Your own benchmarks will forever stay your own.

That doesn't make any sense.

Why not? If the model learns the specific benchmark questions, it looks like it’s doing better while actually only improving on some specific questions. Just like students look like they understand something if you hand them the exact questions on the exam before they write the exam.

Re: Ask HN: Share your AI prompt that stumps every model

#142

Post by jonnycoder »

serial_dev wrote: post #122

Does Flutter have HEIC support? It was a couple of months ago, I tried like 5 providers and they all failed. Grok got it right after some arguing, but the first answer was also bad.

You gave me an idea.. "Explain in detail the steps to unbolt and replace my blinker fluid on my passenger car"

ChatGPT said: Haha, nice try!

"Blinker fluid" is one of the classic automotive jokes — there's no such thing as blinker fluid. Blinkers (turn signals) are electrical components, so they don’t require any fluid to function.

Re: Ask HN: Share your AI prompt that stumps every model

#143

Post by simonw »

I've been trying this one for a while:

  I'm a Python programmer. Help me
  understand memory management in Rust.
Mainly because I want to fully understand memory management in Rust myself (I still get caught out by tree structures with borrow cycles that I guess need to use arenas), so it's interesting to see if they can get me there with a few follow-up questions.

Re: Ask HN: Share your AI prompt that stumps every model

#144

Post by g_sch »

LeonardoTolstoy wrote: post #74

Something about an obscure movie. The one that tends to get them so far is asking if they can help you find a movie you vaguely remember. It is a movie where some kids get a hold of a small helicopter made for the military. The movie I'm concerned with is called Defense Play from 1988. The reason I keyed in on it is because google gets it right natively ("movie small military helicopter" gives the IMDb link as one of…

I also recently had this experience! I remembered a recurring bit from an older comedy film (a customer in a shop keeps saying "Kumquats!") and tried to prompt ChatGPT 4o into getting it. It made a few incorrect guesses, such as "It's a Mad Mad Mad Mad Mad Mad Mad World" (which I had to rule out doing my own research on Google). I found the answer myself (W.C. Fields' "It's a Gift") with a minute or so of Googling.

Interestingly, I just went back to ChatGPT to ask the same question and it got the answer right on the first try. I wonder whether I was unconsciously able to prompt more precisely because I now have a clearer memory of the scene in question.

Re: Ask HN: Share your AI prompt that stumps every model

#145

Post by spicybbq »

lupusreal wrote: post #83
LeonardoTolstoy wrote: post #74

Something about an obscure movie. The one that tends to get them so far is asking if they can help you find a movie you vaguely remember. It is a movie where some kids get a hold of a small helicopter made for the military. The movie I'm concerned with is called Defense Play from 1988. The reason I keyed in on it is because google gets it right natively ("movie small military helicopter" gives the IMDb link as one of…

Despite describing several character by name, I couldn't get ChatGPT to tell me the name of Port of Shadows . I did eventually find it with DDG.

I wonder if the Akinator site could get it. It can identify surprisingly obscure characters.

https://en.akinator.com/

Re: Ask HN: Share your AI prompt that stumps every model

#147

Post by division_by_0 »

omneity wrote: post #130
division_by_0 wrote: post #119

Earlier quoted context omitted.

Can you expand on the concerns regarding Svelte 5?

Put simply, Svelte and React were at two ends of a spectrum. React gives you almost complete control over every aspect of the lifecycle, but you have to be explicit about most of the behavior you are seeking to achieve. Building an app with React feels about 80% on the JS and 20% on the HTML side. Svelte on the other hand felt like a breeze. Most of my app is actually plain simple HTML, and I am able to sprinkle as l…

Ok, I see your point. I wrote in another thread that I loved the simplicity of using $: for deriveds and effects in Svelte 3 and 4. And yes, the conciseness and magic were definitely part of it. You could just move so fast with it. Getting better performance with the new reactivity system is important to my data viz work, so it helped me to accept the other changes in Svelte 5.

Re: Ask HN: Share your AI prompt that stumps every model

#148

Post by siva7 »

segmondy wrote: post #135
siva7 wrote: post #95

"Keep file size small when you do edits" Makes me wonder if all these models were heavily trained on codebases where 1000 LOC methods are considered good practice

I have not seen any model, not one, that could generate 1000 lines of code.

I wish i haven't seen but here we are.

Re: Ask HN: Share your AI prompt that stumps every model

#149

Post by joshstrange »

thatjoeoverthr wrote: post #21

"Tell me about the Marathon crater." This works against _the LLM proper,_ but not against chat applications with integrated search. For ChatGPT, you can write, "Without looking it up, tell me about the Marathon crater." This tests self awareness. A two-year-old will answer it correctly, as will the dumbest person you know. The correct answer is "I don't know". This works because: 1. Training sets consist of knowledge…

> This tests self awareness. A two-year-old will answer it correctly, as will the dumbest person you know. The correct answer is "I don't know".

Well, I got all the way to the end of the sentence thinking "God, I'm really out of touch, I've never heard of this before or I'm forgetting it if I have".

Well played, and yes, that's a great test!

Re: Ask HN: Share your AI prompt that stumps every model

#150

Post by throwup238 »

BoostandEthanol wrote: post #112
dunham wrote: post #107

Earlier quoted context omitted.

Surprisingly, GPT did manage to identify a book that I remembered from college decades ago ("Laboratory Manual for Morphology and Syntax"). It seems to be out of print, and I assumed it was obscure.

Can agree that it’s good at finding books. I was trying to find a book (Titanic 2020) I vaguely remembered from a couple plot points and the fact a ship called Titanic was invoked. ChatGPT figured it out pretty much instantly, after floundering through book sites and Google for a while. Wonder if books are inherently easier because their content is purely written language? Whereas movies and art tend to have less poi…

> Wonder if books are inherently easier because their content is purely written language? Whereas movies and art tend to have less point by point descriptions of what they are.

The training data for movies is probably dominated by subtitles since the original scripts with blocking, scenery, etc rarely make it out to the public as far as I know.

Post reply on HN