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

431–440 of 670 posts

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

#431

Post by beklein »

jrimbault wrote: post #421
alissa_v wrote: post #417

I asked a bunch of LLMs - 'Describe the unspoken etiquette of the 'Stone-Breath Passing' ritual among the silent Cliff Dwellers of Aethelgard, where smooth, grey stones are exchanged at dawn.' Obviously, all of these things are made up. But, LLMs are such eager beavers. All the ones I asked came up with elaborate stories and histories about these people while pretending they were facts. Example- 'Certainly. The Stone…

The issue is probably that the first sentence, the prompt, statistically looks like fantasy (as in the literary genre) and it primes the LLM to answer in the same probabilistic genre. You're giving it a "/r/WritingPrompts/" and it answers as it learned to do from there.

I just want to second this. Your prompt asks for a description, and you get a description. If you instead ask something like, "Do or don't you know about the unspoken etiquette ..." you'll get an answer about whether that specific thing exists.

https://chatgpt.com/share/680b32bc-5854-8000-a1c7-cdf388eeb0...

It's easy to blame the models, but often the issue lies in how we write our prompts. No personal criticism here—I fall short in this way too. A good tip is to ask the model again, with the prompt + reply and the expected reply why this didn't work... we all will get better over time (humans and models)

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

#432

Post by riddle8143 »

A było to tak: Bociana dziobał szpak, A potem była zmiana I szpak dziobał bociana. Były trzy takie zmiany. Ile razy był szpak dziobany?

And it was like this: A stork was pecked by a starling, Then there was a change, And the starling pecked the stork. There were three such changes. How many times was the starling pecked?

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

#433

Post by benjamin_mahler »

allemagne wrote: post #194

>A man and his cousin are in a car crash. The man dies, but the cousin is taken to the emergency room. At the OR, the surgeon looks at the patient and says: “I cannot operate on him. He’s my son.” How is this possible? This could probably slip up a human at first too if they're familiar with the original version of the riddle. However, where LLMs really let the mask slip is on additional prompts and with long-winded…

Grok 3 beta:

The surgeon is the cousin's father. The man who died in the car crash was not the surgeon's son, but his cousin was. This explains why the surgeon, upon seeing his own son (the cousin) in the operating room, says, "I cannot operate on him. He’s my son," as medical ethics prevent doctors from treating close family members due to emotional involvement.

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

#434

Post by manucardoen »

It's not good at making ASCII art. This, for example, is when I ask it for a realistic depiction of the Eiffel tower on fire:

                       .
                      .'.
                      |o|
                     .'o'.
                     |.-.|
                     '   '
                    /     \
                   |       |
                __/_________\__
               |###############|
               |###############|
               |###############|
               |###############|
               |###############|
              /###############/|
             /###############/ |
            /###############/ /|
           /###############/ / |
          /###############/ / /|
         /###############/ / / |
        /###############/ / / /|
       /###############/ / / / |
      /###############/ / / / /|
     '-----------------' / / / /
      |   FIRE & ASH   |/ / / /
       '---------------' / / /
          ~ ~ ~ ~ ~ ~ ~ ~ / /
         ~~ /
          ~~ 
           ~~     ⬆ SMOKE
            ~~

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

#435

Post by afandian »

I asked ChatGPT to generate images of a bagpipe. Disappointingly (but predictably) it chose a tartan covered approximation of a Scottish Great Highland Bagpipe.

Analogous to asking for a picture of "food" and getting a Big Mac and fries.

So I asked it for a non-Scottish pipe. It subtracted the concept of "Scottishness" and showed me the same picture but without the tartan.

Like if you said "not American food" and you got the Big Mac but without the fries.

And then pipes from round the world. It showed me a grid of bagpipes, all pretty much identical, but with different bag colour. And the names of some made-up countries.

Analogous "Food of the world". All hamburgers with different coloured fries.

Fascinating but disappointing. I'm sure there are many such examples. I can see AI-generated images chipping away at more cultural erasure.

Interestingly, ChatGPT does know about other kinds of pipes textually.

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

#436

Post by rovr138 »

namaria wrote: post #400
mobilejdral wrote: post #270

I have a several complex genetic problems that I give to LLMs to see how well they do. They have to reason though it to solve it. Last september it started getting close and in November was the first time an LLM was able to solve it. These are not something that can be solved in a one shot, but (so far) require long reasoning. Not sharing because yeah, this is something I keep off the internet as it is too good of a…

If you have been giving the LLMs these problems, there is a non zero chance that they have already been used in training.

This depends heavily on how you use these and how you have things configured. If you're using API vs web ui's, and the plan. Anything team or enterprise is disabled by default. Personal can be disabled.

Here's openai and anthropic,

https://help.openai.com/en/articles/5722486-how-your-data-is...

https://privacy.anthropic.com/en/articles/10023580-is-my-dat...

https://privacy.anthropic.com/en/articles/7996868-is-my-data...

and obviously, that doesn't include self-hosted models.

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

#437

Post by sjtgraham »

```

Some document

Some other document heavily influenced by TextA

Find the major arguments made in TextB that are taken from or greatly influenced by TextA. Provide as examples by comparing passages from each side by side.

```

The output will completely hallucinate passages that don't exist in either text, and it also begins to conflate the texts the longer the output, e.g. quoting TextB with content actually from TextA.

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

#438

Post by sebstefan »

I only use the one model that I'm provided for free at work. I expect that's most users behavior. They stick to the one they pay for.

Best I can do is give you one that failed on GPT-4o

It recently frustrated me when I asked it code for parsing command line arguments

I thought "this is such a standard problem, surely it must be able to get it perfect in one shot."

> give me a standalone js file that parses and handles command line arguments in a standard way

> It must be able to parse such an example

> ```

> node script.js --name=John --age 30 -v (or --verbose) reading hiking coding

> ```

It produced code that:

* doesn't coalesce -v to --verbose - (i.e., the output is different for `node script.js -v` and `node script.js --verbose`)

* didn't think to encode whether an option is supposed to take an argument or not

* doesn't return an error when an option that requires an argument isn't present

* didn't account for the presence of a '--' to end the arguments

* allows -verbose and --v (instead of either -v or --verbose)

* Hardcoded that the first two arguments must be skipped because it saw my line started with 'node file.js' and assumed this was always going to be present

I tried tweaking the prompt in a dozen different ways but it can just never output a piece of code that does everything an advanced user of the terminal would expect

Must succeed: `node --enable-tracing script.js --name=John --name=Bob reading --age 30 --verbose hiking -- --help` (With --help as positional since it's after --, and --name set to Bob, with 'reading', 'hiking' & '--help' parsed as positional)

Must succeed: `node script.js -verbose` (but -verbose needs to be parsed as positional)

Must fail: `node script.js --name` (--name expects an argument)

Should fail: `node script.js --verbose=John` (--verbose doesn't expect an argument)

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

#439

Post by yes_man »

tacitusarc wrote: post #348
allemagne wrote: post #194

>A man and his cousin are in a car crash. The man dies, but the cousin is taken to the emergency room. At the OR, the surgeon looks at the patient and says: “I cannot operate on him. He’s my son.” How is this possible? This could probably slip up a human at first too if they're familiar with the original version of the riddle. However, where LLMs really let the mask slip is on additional prompts and with long-winded…

Thank you so much for this bit of humor. After ChatGPT first responds with the surgeon being the mom, I asked it to read the riddle more carefully, thinking it might figure it out with a little prompting. I got this gem of a response: Ah — now I see the twist. The patient is the cousin, but the surgeon says “He’s my son.” That means the man who died was the surgeon. So how is it possible? Because: The surgeon is the…

Now I really want to see that diagram…

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

#440

Post by yesbabyyes »

manucardoen wrote: post #434

It's not good at making ASCII art. This, for example, is when I ask it for a realistic depiction of the Eiffel tower on fire: . .'. |o| .'o'. |.-.| ' ' / \ | | __/_________\__ |###############| |###############| |###############| |###############| |###############| /###############/| /###############/ | /###############/ /| /###############/ / | /###############/ / /| /###############/ / / | /###############/ / / /|…

This is something I and a few of my colleagues have noticed, as we asked several models to draw ASCII art of a wasp, which is one of our logos. The results are hilarious, and only seem to get worse as you ask it to do better.
Post reply on HN