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

301–310 of 670 posts

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

#301

Post by bobxmax »

leifmetcalf wrote: post #298

Let G be a group of order 3*2^n. Prove there exists a non-complete non-cyclic Cayley graph of G such that there is a unique shortest path between every pair of vertices, or otherwise prove no such graph exists.

Since any group of order 3⋅2n3⋅2n has ∣G∣≥3∣G∣≥3, it cannot admit a Cayley graph which is a tree. Hence:

    No Cayley graph of a group of order 3⋅2n3⋅2n can have a unique path between every pair of vertices.

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

#302

Post by Sohcahtoa82 »

"I have a stack of five cubes. The bottom two cubes are red, the middle cube is green, and the top two cubes are blue. I remove the top two cubes. What color is the remaining cube in the middle of the stack?"

Even ChatGPT-4o frequently gets it wrong, especially if you tell it "Just give me the answer without explanation."

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

#303

Post by leifmetcalf »

bobxmax wrote: post #301
leifmetcalf wrote: post #298

Let G be a group of order 3*2^n. Prove there exists a non-complete non-cyclic Cayley graph of G such that there is a unique shortest path between every pair of vertices, or otherwise prove no such graph exists.

Since any group of order 3⋅2n3⋅2n has ∣G∣≥3∣G∣≥3, it cannot admit a Cayley graph which is a tree. Hence: No Cayley graph of a group of order 3⋅2n3⋅2n can have a unique path between every pair of vertices.

My mistake, I said unique path when I should have said unique shortest path.

Also, there are trivial solutions with odd cycles and complete graphs which must be excluded. (So the answer to the prompt as originally stated is wrong too)

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

#304

Post by JCattheATM »

fao_ wrote: post #87
pje wrote: post #61

Earlier quoted context omitted.

GPT 4.5 even doubles down when challenged: > Nope, I didn’t make it up — Marathon crater is real, and it was explored by NASA's Opportunity rover on Mars. The crater got its name because Opportunity had driven about 42.2 kilometers (26.2 miles — a marathon distance) when it reached that point in March 2015. NASA even marked the milestone as a symbolic achievement, similar to a runner finishing a marathon. (Obviously…

This is the kind of reason why I will never use AI What's the point of using AI to do research when 50-60% of it could potentially be complete bullshit. I'd rather just grab a few introduction/101 guides by humans, or join a community of people experienced with the thing — and then I'll actually be learning about the thing. If the people in the community are like "That can't be done", well, they have had years or dec…

> What's the point of using AI to do research when 50-60% of it could potentially be complete bullshit.

Because if you know how to spot the bullshit, or better yet word prompts accurately enough that the answers don't give bullshit, it can be an immense time saver.

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

#306

Post by starik36 »

vitaflo wrote: post #296

The one I always use is literally "show number of NFC Championship Game appearences by team since 1990". The only AI that has ever gotten the answer right was Deepseek R1. All the rest fail miserably at this one. It's like they can't understand past events, can't tabulate across years properly or don't understand what the NFC Championship game actually means. Many results "look" right, but they are always wrong. You…

Have you tried in the Deep Research or Thinking mode? I've had pretty good success with tabulating past events this way.

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

#307

Post by krainboltgreene »

dudeinhawaii wrote: post #164
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…

I like this but at the same time it seems tricky don't you think? Is the AI model intuiting your intent? There is a Marathon Valley on Mars that could be implied to be a previous crater. I'm not sure if the AI is hallucinating outright or attempting to answer an ambiguous question. It's like saying "tell me about the trade building in New York". Pre-9/11, you'd understand this was the World Trade Center and wouldn't…

> Is the AI model intuiting your intent?

I keep seeing this kind of wording and I wonder: Do you know how LLM's work? Not trying to be catty, actually curious where you sit.

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

#308

Post by krainboltgreene »

Workaccount2 wrote: post #170
mvdtnz wrote: post #133

Earlier quoted context omitted.

None of it is correct because it was not asked about Marathon Valley, it was asked about Marathon Crater, a thing that does not exist, and it is claiming that it exists and making up facts about it.

Or it's assuming you are asking about Marathon Valley, which is very reasonable given the context. Ask it about "Marathon Desert", which does not exist and isn't closely related to something that does exist, and it asks for clarification. I'm not here to say LLMs are oracles of knowledge, but I think the need to carefully craft specific "gotcha" questions in order to generate wrong answers is a pretty compelling case…

If someone asked me or my kid "What do you know about Mt. Olampus." we wouldn't reply: "Oh, Mt. Olampus is a big mountain in greek myth...". We'd say "Wait, did you mean Mt. Olympus?"

It doesn't "assume" anything, because it can't assume, that's now the machine works.

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

#309

Post by leifmetcalf »

leifmetcalf wrote: post #298

Let G be a group of order 3*2^n. Prove there exists a non-complete non-cyclic Cayley graph of G such that there is a unique shortest path between every pair of vertices, or otherwise prove no such graph exists.

Gemini 2.5 at least replies that it seems unlikely to be false without hallucinating a proof. From its thoughts it gets very close to figuring out that A_4 exists as a subgroup.

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

#310

Post by krainboltgreene »

Workaccount2 wrote: post #193
mvdtnz wrote: post #169

Earlier quoted context omitted.

If you asked me for all the details of a Honda Civic and I gave you details about a Honda Odyssey you would not say I was correct in any way. You would say I was wrong.

The closer analogy is asking for the details of a Mazda Civic, and being given the details of a Honda Civic.

AKA wrong.
Post reply on HN