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

41–50 of 78 posts

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

#41

Post by basch »

simlevesque wrote: post #36
basch wrote: post #23

Earlier quoted context omitted.

Since its unclear whats going on, Gemini first gave me some python. import random random_number = random.randint(1, 10) print(f"{random_number=}") Then it stated the output. Code output random_number=8 "This time, the dice landed on 8." Code output random_number=9 "Your next random number is 9." I would guess its not actually executing the python it displayed? Just a simulation, right?

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?

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

#42

Post by hhh »

basch wrote: post #23
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

Since its unclear whats going on, Gemini first gave me some python. import random random_number = random.randint(1, 10) print(f"{random_number=}") Then it stated the output. Code output random_number=8 "This time, the dice landed on 8." Code output random_number=9 "Your next random number is 9." I would guess its not actually executing the python it displayed? Just a simulation, right?

Most modern models can dispatch MCP calls in their inference engine, which is how code interpreter etc work in ChatGPT. Basically an mcp server that the execution happens as a call to their ai sandbox and then returns it to the llm to continue generation.

You can do this with gpt-oss using vLLM.

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

#43

Post by egeozcan »

paxys wrote: post #6

The part about injecting randomness is the most intersting bit of the article. So if you want your LLM responses to be more distributed (beyond what setting the temperature will allow), add some random english words to the start of the prompt.

In a way that sounds like setting the seed.

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

#44

Post by rishabhaiover »

bogzz wrote: post #27
rishabhaiover wrote: post #18

Earlier quoted context omitted.

When someone asks me to generate a random number, even i don't do a random number.

I used to always reflexively blurt out 67 when asked for a random number. I'm a proto gen alpha. I 6-7'd before it was cool.

For a second I assumed you meant 69 but then it hit me, i'm getting old.

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

#45

Post by emp17344 »

wyldfire wrote: post #7

"I expected an automaton to be a good source of entropy and it turns out it is not." BTW LLM here is doing a great job of emulating humans. They are not good at this task either. > Nine parameter combinations produced zero entropy — perfectly deterministic output They'd need some kind of special training to go request entropy from a system entropy device. Behaving deterministically is a feature, not a bug.

Just because the LLM happens to be bad at something humans are also bad at, doesn’t mean the system is “emulating humans”.

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

#46

Post by paxys »

egeozcan wrote: post #43
paxys wrote: post #6

The part about injecting randomness is the most intersting bit of the article. So if you want your LLM responses to be more distributed (beyond what setting the temperature will allow), add some random english words to the start of the prompt.

In a way that sounds like setting the seed.

Kinda, but the same seed will not guarantee the same result the next time around.

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

#47

Post by FrancoisBosun »

paxys wrote: post #6

The part about injecting randomness is the most intersting bit of the article. So if you want your LLM responses to be more distributed (beyond what setting the temperature will allow), add some random english words to the start of the prompt.

Meh, I tell it "use uuidgen and get your randomness from that". Of course, that won't work on ChatGPT web, but works well enough on the command line.

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

#48

Post by simlevesque »

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?

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.

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

#49

Post by Slow_Hand »

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 regards."

Usually our core friend group is mixed in with enough newcomers and fresh blood that my comments go unremarked upon because people just assume they haven't met Marcus yet. That he's someone else's acquaintance.

A few of my friends have gotten wise to the joke. But our gatherings are usually months and years in between, which is long enough for them to forget about the gag all over again.

Post reply on HN