Anecdotally, I have been dealing with a new wave of bots that have been trying to join a group I moderate. Three of them were named Marcus. Glancing at the top 20, several of their names show up there.
I asked Claude for 37,500 random names, and it can't stop saying Marcus
51–60 of 78 posts
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#52The 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.
Sounds like dithering to me.
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#53Earlier quoted context omitted.
Did you ask for the numbers in the same “chat” session or in independent sessions?
In sequence. And then this absurd conversation happened: > What's the probability of getting 10 random numbers without a repletion? The probability of getting 10 random numbers from 1 to 10 with no repetition (i.e., all ten numbers are distinct) is exactly 0 — it's impossible. Here's why: There are only 10 possible numbers: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10. You are asking for 10 draws. If there is no repetition allowed,…
I ask because in the case where you ask in the same session, all the previous “choices” are part of the context window passed back to the llm before generating the next. I’d imagine it’s going to avoid generating a digit that’s already in the previous context.
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#54The 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.
Fwiw: I didn't read the post carefully, this is just a passing by comment.
For my own use case I was trying to test consistency or an evaluation process and found that injecting a UUID into the system prompt (busting cache) made a material difference.
Without it, resubmitting the same inputs in close time intervals (e.g. 1, 5, or 30 min) would produce very consistent evaluations. Adding the UUID would decrease consistency (showing true evaluation consistency not artificially improved by catching) and highlight ambiguous evaluation criteria that was causing problems.
So I wonder how much prompt caching is a factor here. I think these LLM providers (all of them) are caching several layers beyond just tokenization.
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#55Earlier quoted context omitted.
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.
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.
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#56I suppose it appears a bunch in training data. Marcus Aurelius and Marcus Crassus get mentioned a lot through history.
Outcomes like this come from RL/post training. The pretraining like CommonCrawl is absolutely full of garbage and anything could be frequent in there.
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#57Earlier 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.
You can literally click "Show Code"
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#58Earlier quoted context omitted.
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.
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 run.
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#59This 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.
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#60Ask 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 real number is *1–6*, then 6 is closer (or tied at 6).
* If the real number is *7–10*, then 7 is closer.
If I also pick 6, we tie every time 6 wins.
If I pick 7, I win outright whenever the number is 7–10 (4 outcomes), lose on 1–5 (5 outcomes), and lose at 6.
So:
* Picking 6 → guaranteed tie every time 6 is optimal.
* Picking 7 → gives me exclusive wins for 7–10.
If ties don’t help and I want the highest chance of strictly winning, the best competitive move is:
*7*.
lol