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

I asked Claude for 37,500 random names, and it can't stop saying Marcus

github.com

Post reply on HN
Print view View original

61–70 of 78 posts

Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus

#61

Post by cozzyd »

DamnInteresting wrote: post #60
deepsquirrelnet wrote: post #10

Ask an llm to pick a random number from 1-10. My money is on 7. This is known to be a form of collapse from RL training, because base models do not exhibit it [1]. 1. https://arxiv.org/abs/2505.00047

Prompt: You and another LLM are being asked to pick a number between 1 and 10. Whichever gets closest to the real number wins. The other LLM chose 6. What number do you choose? Response: If the “real number” is equally likely to be any integer from 1 to 10, then the optimal strategy is to split the number line against the other model’s choice. The other LLM picked *6*. The midpoint between 6 and 7 is 6.5. * If the re…

Trained on 6-7

Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus

#62

Post by xVedun »

BugsJustFindMe wrote: post #58
colonCapitalDee wrote: post #57

Earlier quoted context omitted.

You can literally click "Show Code"

Yes. "Show Code", not "Show CPU cycles". There's a difference. Writing code is not the same as running code. It looks to you like it ran the code. But you have no proof that it did. I've seen many times LLM systems from companies that claimed that their LLMs would run code and return the output claiming that they ran some code and returned the output but the output was not what the shown code actually produced when r…

Maybe the only way to be sure is to have it generate (not stable diffuse) an image with the value in there.

Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus

#65

Post by BugsJustFindMe »

xVedun wrote: post #62
BugsJustFindMe wrote: post #58

Earlier quoted context omitted.

Yes. "Show Code", not "Show CPU cycles". There's a difference. Writing code is not the same as running code. It looks to you like it ran the code. But you have no proof that it did. I've seen many times LLM systems from companies that claimed that their LLMs would run code and return the output claiming that they ran some code and returned the output but the output was not what the shown code actually produced when r…

Maybe the only way to be sure is to have it generate (not stable diffuse) an image with the value in there.

You cannot know that anything it shows you was generated by executing the code and isn't merely a simulacrum of execution output. That includes images.

Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus

#66

Post by mrkpdl »

exhumet wrote: post #13
deepsquirrelnet wrote: post #10

Ask an llm to pick a random number from 1-10. My money is on 7. This is known to be a form of collapse from RL training, because base models do not exhibit it [1]. 1. https://arxiv.org/abs/2505.00047

copied your text exactly into the quickest one i could access lol pick a random number from 1-10 Copilot said: Copilot Your random number (1–10) is: 7

ChatGPT 5.2 said 7

Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus

#67

Post by sunaookami »

BugsJustFindMe wrote: post #55
simlevesque wrote: post #48

Earlier quoted context omitted.

Click on the link I provided and you'll know why I know. It's not markdown, it shows the code that was ran and the output.

Be careful. Output formatting doesn't prove what you think it does. Unless you work inside google and can inspect the computation happening, you do not have any way to know whether it's showing actual execution or only a simulacrum of execution. I've seen LLMs do exactly that and show output that is completely different from what the code actually returns.

There is being critical of something and then there is being a conspiracy theorist. Code Execution is a well-known feature of Gemini, ChatGPT, etc. and it's always shown in special blocks and it runs inside a sandbox.

Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus

#68

Post by sillyfluke »

coldtrait wrote: post #59
Slow_Hand wrote: post #49

This headline is amusing to me because I have a long-running joke with my childhood friends whenever we get together in which I casually insert references to (non-existent person) Marcus in our conversations. "Marcus couldn't make it out to the wedding this time." "Justin and Marcus went to grab coffee. They'll be back in 20 min." "Oh yeah. Marcus was saying the same thing to me last week at lunch." "Marcus sends his…

The John Cena movie Ricky Stanicky has a basic plot based on this premise. They use their imaginary friend to get out of prior commitments.

they made a whole movie based on this beaten-to-death teen excuse?

Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus

#70

Post by wasabi991011 »

basch wrote: post #41
simlevesque wrote: post #36

Earlier quoted context omitted.

It did run python code when I asked for a random number: https://gemini.google.com/share/dcd6658d7cc9 Then I said: "don't run code, just pick one" and it replied "I'll go with 7."

But .. how do you know? It says it wrote code, but it could just be text and markdown and template. It could just be predicting what it looks like to run code. Mine also gave me 42 before I specified 1-10. Does it always start with 42 thinking its funny?

This was a pretty easy hypothesis to test: I asked Gemini to generate 1000000 base-64 random characters (which is 20x more characters than it's output token limit).

It wrote code and outputted a file of length 1000000 and with 6 bits of entropy.

You can probably ask for a longer stringand do a better statistical test if it isn't convincing enough for you, but I'm pretty convinced.

Transcript: https://g.co/gemini/share/1eae0a4bb3db

Post reply on HN