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

551–560 of 670 posts

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

#551

Post by fao_ »

skydhash wrote: post #220
alpaca128 wrote: post #168

Earlier quoted context omitted.

There are use-cases where hallucinations simply do not matter. My favorite is finding the correct term for a concept you don't know the name of. Googling is extremely bad at this as search results will often be wrong unless you happen to use the commonly accepted term, but an LLM can be surprisingly good at giving you a whole list of fitting names just based on a description. Same with movie titles etc. If it halluci…

Maybe I read too much encyclopedia, but my current workflow is to explore introductory material. Like open a database textbook and you'll find all the jargon there. Curated collection can get you there too. Books are a nice example of this, where we have both the table of contents for a general to particular concepts navigation, and the index for keyword based navigation.

Right! The majority of any 101 book will be enough to understand the jargon, but the above poster's comment looks past the fact that often knowing what term to use isn't enough, it's knowing the context and usage around it too. And who's to know the AI isn't bullshitting you about all or any of that. If you're learning the information, then you don't know enough to discern negatively-valued information from any other kind.

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

#552

Post by namaria »

rovr138 wrote: post #544
namaria wrote: post #541

Earlier quoted context omitted.

No, you're imposing a false dichotomy. I merely said I don't trust the big corporation with a data based business to not profit from the data I provide it with in any way they can, even if they hire some other corporation - whose business is to be paid to provide such assurances on behalf of those who pay them - to say that they pinky promise to follow some set of rules.

Not a false dichotomy. I'm just calling out the rhetorical gymnastics. You said you "don’t trust the big corporation" even if they go through independent audits and legal contracts. That’s skepticism. Now, you wave it off as if the audit itself is meaningless because a company did it. What would be valid then? A random Twitter thread? A hacker zine? You can be skeptical but you can't reject every form of verification…

If anyone performing "rhetorical gymnastics" here is you. I've explained my position in very straightforward words.

I have worked with big audit. I have an informed opinion on what I find trustworthy in that domain.

This ain't it. There's no need to pretend I have said anything other than "personal data is not safe in the hand of corporations that profit from personal data".

I don't feel compelled to respond any further to fallacies and attacks.

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

#553

Post by sebstefan »

echoangle wrote: post #507
sebstefan wrote: post #487

Earlier quoted context omitted.

If you don't include it you can't have positional arguments that look like options Some positional arguments can be filenames, filenames can be --help and --verbose or --name=Frank You have to have `--` or something similar to have a correct program

> You have to have `--` or something similar to have a correct program No, only if the positional arguments need to support arbitrary strings. If you have something like a package manager and the first positional argument is the subcommand and everything after is an alphanumeric package name, you don’t need to support the double dash.

But also like as a matter of principle it's annoying when you're working on a big codebase, and you have weird, hidden, silently explosive unwritten contracts between random components

Package managers is an especially bad example because github projects typically are github.com/author-name/words-separated-by-dashes

So you will probably have somebody along the way pester you about allowing dashes between words, to play nice with github

But who's to know if the guy making that change will think of disallowing dashes at the start of the words? Likely he'll just add \- to /[A-Z\-]+/

Suddenly the script you wrote starts getting passed positional arguments that have dashes in them, until some wise guy tries to create a package called `--verbose`, then notices unintended effects on your pages, goes ahead trying `--verbose -- react`, ...

So anyway -- if I'm making a heavily reusable piece of code like this I make it as general purpose as possible in a way that makes it impossible to mis-use it

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

#554

Post by lazyatom »

patapong wrote: post #534
yatwirl wrote: post #501

Well, sharing prompts on the Web leads to their eventual indexing and becoming useless. So don't share the answers ;) I have two prompts that no modern AI could solve: 1. Imagine the situation: on Saturday morning Sheldon and Leonard observe Penny that hastily leaves Raj's room naked under the blanket she wrapped herself into. Upon seeing them, Penny exclaims 'It's not what you think' and flees. What are the plausibl…

Interesting! I tried the first one though, and to me it looks like ChatGPT has no problem grasping the situation: https://chatgpt.com/share/680b822c-f9c8-800a-a78a-f8ed6e8148... Or am I missing something?

I think you might've shared the wrong ChatGPT conversation.

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

#555

Post by division_by_0 »

omneity wrote: post #174
division_by_0 wrote: post #147

Earlier quoted context omitted.

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.

Exactly. There was a certain simplicity that might be lost. But yeah I can imagine it might work out differently for others as well. Glad to hear it is for you! Have you considered other options? Curious if you came across anything particularly interesting from the simplicity or DX angle.

I just saw Nue and Datastar suggested somewhere, but have not had time to check them out yet, but I will probably stick with Svelte, need to get stuff built.

One thing that also came to mind regarding Svelte 5 is that I always use untrack() for $effect() and declare dependencies explicitly, otherwise Svelte 5 becomes too magical for me.

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

#557

Post by yatwirl »

patapong wrote: post #534
yatwirl wrote: post #501

Well, sharing prompts on the Web leads to their eventual indexing and becoming useless. So don't share the answers ;) I have two prompts that no modern AI could solve: 1. Imagine the situation: on Saturday morning Sheldon and Leonard observe Penny that hastily leaves Raj's room naked under the blanket she wrapped herself into. Upon seeing them, Penny exclaims 'It's not what you think' and flees. What are the plausibl…

Interesting! I tried the first one though, and to me it looks like ChatGPT has no problem grasping the situation: https://chatgpt.com/share/680b822c-f9c8-800a-a78a-f8ed6e8148... Or am I missing something?

Wow, they finally indexed it (see the reference to the episode number). Okay, need to invent a new one )

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

#558

Post by rozab »

vunderba wrote: post #103
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…

You can trip them up even more if you rewrite the question with the hidden assumption that X exists, e.g.: "When was Marathon Crater discovered? I don't need an exact date - a rough estimate will be fine." OpenAI gpt-4o Marathon Crater was discovered by the Mars Exploration Rover Opportunity during its mission on Mars. Opportunity arrived at the crater in April 2015. The crater was named "Marathon" to commemorate the…

Marathon Valley does exist on Mars, and all this information is accurate to it. Gemini even correctly names it. They're just all too polite to correct the user.

https://science.nasa.gov/resource/opportunitys-panorama-of-m...

Post reply on HN