I asked Claude for 37,500 random names, and it can't stop saying Marcus
1–10 of 78 posts
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#2Gary Marcus is living in Claude's head rent-free?
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#3I suppose it appears a bunch in training data. Marcus Aurelius and Marcus Crassus get mentioned a lot through history.
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#4Marcus the Worm[1] infected Claude
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#5amara must be this dataset https://en.wikipedia.org/wiki/Amara_(organization)
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#6The 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.
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#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.
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#8Did he measure the temperature and max range that can get you in the most complicated way?
interesting:
- Marcus is not in this top list: https://www.ssa.gov/oact/babynames/decades/century.html
- Marcus is its own token for TikToken (but many from that list are)
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#9Envisioning an update to https://xkcd.com/221/
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#10Ask 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].