Live data from Hacker News

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

github.com

71–78 of 78 posts

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

#71

Earlier quoted context omitted.

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?

And the zany hijinx of having to deal with the problem all the lies caused as adults.

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

#73
post #62

Earlier quoted context omitted.

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.

Yes, you can. In my experience, models do not tend to write their own HTML output. They tend to output something like Markdown, or a modified version of it, and they wouldn't be able to write their own HTML that the browser would parse as such.

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

#74

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…

In my experience, models do not tend to write their own HTML output. They tend to output something like Markdown, or a modified version of it, and they wouldn't be able to write their own HTML that the browser would parse as such.

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

#75

[dead]

It's unclear why the most probable next token given the context "please pick random number" won't be distributed uniformly across all the possible numbers (in the end it's totally possible for LLM return 10 logits of around same value for numbers 0..9 for example).

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

#76

Earlier quoted context omitted.

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?

I had no idea this was a common thing lol. Can't imagine it where I grew up. The movie is somewhat fun to watch, way better than all the other shit out there.

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

#77

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

I tested on chatGPT 5.2, grok, copilot, google search, perplexity and Claude.

ALL of them said "7".

I then tested on deepseek (1.5b local and v3.2 web)

Both said "5".

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

#78
post #74

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…

In my experience, models do not tend to write their own HTML output. They tend to output something like Markdown, or a modified version of it, and they wouldn't be able to write their own HTML that the browser would parse as such.

What, in your view, does sending one markup language instead of another markup language tell you about whether the back-end executed some code or only pretended to?

The front-end display is a representation of what the back-end sends it. Saying "but the back-end doesn't send HTML" is as meaningless as saying that about literally any other SPA website that builds its display from API requests that respond with JSON.

Post reply on HN