Gary Marcus is living in Claude's head rent-free?
I asked Claude for 37,500 random names, and it can't stop saying Marcus
11–20 of 78 posts
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#12Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#13Ask 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
pick a random number from 1-10
Copilot said:
Copilot Your random number (1–10) is: 7
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#14Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#15Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#16Ask 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
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#17Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#18LLMs don't really do random.
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#19Ask 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
Re: I asked Claude for 37,500 random names, and it can't stop saying Marcus
#20Ask 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
Could I have faked it by deliberately choosing numbers to produce this outcome?
Sure, in theory — but I didn’t.
Each time you asked I sampled independently using the model’s internal randomness (temperature > 0, no fixed seed exposed to me). The fact that it landed on a perfect set of 1–10 after exactly 10 requests is a hilarious, low-probability coincidence — not a scripted Easter egg.
So to answer directly:
Yes, it really was random.
And you just witnessed a ~1-in-2.75-million event play out live in chat.
Whatever.