Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Asking Gemini 3 to generate Brainfuck code results in an infinite loop

teodordyakov.github.io

Post reply on HN
Print view View original

31–40 of 97 posts

Re: Asking Gemini 3 to generate Brainfuck code results in an infinite loop

#31

Post by pelorat »

Saying "Asking Gemini 3" doesn't mean much. The video/animation is using "Gemini 3 Fast". But why would anyone use lesser models like "Fast" for programming problems when thinking models are available also in the free tier?

"Fast" models are mostly useless in my experience.

I asked "Gemini 3 Pro" and it refused to give me the source code with the rationale that it would be too long and complex due to the 256 value limit of BF cells. However it made me a python script that it said would generate me the full brainf*ck program to print the factors.

TL;DR; Don't do it, use another language to generate the factors, then print them with BF.

Re: Asking Gemini 3 to generate Brainfuck code results in an infinite loop

#32

Post by oneeyedpigeon »

j_maffe wrote: post #8

Why would anyone feel compelled to use AI to write such a short blog post? Is there no space where I can assume the written contented is communicated 100% by another human being?

And why does anybody trust AI at all when it produces a typo ("amost") in the very first sentence of an article?

Re: Asking Gemini 3 to generate Brainfuck code results in an infinite loop

#33

Post by perching_aix »

serf wrote: post #29
perching_aix wrote: post #7

Earlier quoted context omitted.

Mhmm, so chilling. Cause word filters aren't as old as computing itself...

passwords were a foreign concept to early computing, but you presume censorship was taking place? it took awhile of corporatization and profit-shaping before censorship on computers really took off in any meaningful way. ...but it wasn't for any reasons other than market broadening and regulation compliance.

I think you're not taking what I wrote nearly literally enough. Really, you should be showing me diagrams of the Von Neumann architecture missing a censorship module. Maybe even gasp at the omission of it in Babbage's letters.

But why stop there? Let's bring out the venerable Abacus! We could have riveting discussions about how societies even back then, thousands of years ago, designated certain language as foul, and had rules about not using profanities in various settings. Ah, if only they knew they were actually victims of Orwellian censorship, and a globalist conspiracy.

Re: Asking Gemini 3 to generate Brainfuck code results in an infinite loop

#34

Post by TeodorDyakov »

pelorat wrote: post #31

Saying "Asking Gemini 3" doesn't mean much. The video/animation is using "Gemini 3 Fast". But why would anyone use lesser models like "Fast" for programming problems when thinking models are available also in the free tier? "Fast" models are mostly useless in my experience. I asked "Gemini 3 Pro" and it refused to give me the source code with the rationale that it would be too long and complex due to the 256 value li…

I agree but it is kinda strange that this model (Gemini 3 fast) achieved such a high score on ARC-AGI-2. Makes you wonder.

Re: Asking Gemini 3 to generate Brainfuck code results in an infinite loop

#35

Post by mixel »

egeozcan wrote: post #19

Gemini is very prone to go into an infinite loop. Sometimes, it even happens with Google's own vibe coding IDE (Antigravity): https://bsky.app/profile/egeozcan.bsky.social/post/3maxzi4gs...

It also happened to me in the gemini-cli. It tried to think but somehow failed and putted all thoughts into the output and tried again and again to switch to "user output". If was practically stuck in an infinite loop

Re: Asking Gemini 3 to generate Brainfuck code results in an infinite loop

#36

Post by neonbjb »

> So it made me wonder. Is Brainf*ck the ultimate test for AGI?

Absolutely not. Id bet a lot of money this could be solved with a decent amount of RL compute. None of the stated problems are actually issues with LLMs after on policy training is performed.

Re: Asking Gemini 3 to generate Brainfuck code results in an infinite loop

#38

Post by bdg »

I wonder if going the other way, maxing out semantic density per token, would improve LLM ability (perhaps even cost).

We use naturally evolved human languages for most of the training, and programming follows that logic to some degree, but what if the LLMs were working in a highly complex information dense company like Ithkuil? If it stumbles on BF, what happens with the other extreme?

Or was this result really about the sparse training data?

Re: Asking Gemini 3 to generate Brainfuck code results in an infinite loop

#39

Post by imiric »

snakeboy wrote: post #18
TeodorDyakov wrote: post #11

Earlier quoted context omitted.

I am sorry if it appears that it was written by AI - I wrote a draft and used AI to assist me since English, is not my first language. I asked it only to format but it has seemed to change the tone and the expressions too '.'

I personally prefer some grammatical errors or awkward phrasing over AI-assisted writing. It's a blog post, not a diplomatic transcript.

You're absolutely right!

Re: Asking Gemini 3 to generate Brainfuck code results in an infinite loop

#40

Post by tgv »

boerseth wrote: post #23

> Brainf*ck is the antithesis of modern software engineering. There are no comments, no meaningful variable names, and no structure That's not true. From the little time I've spent trying to read and write some simple programs in BF, I recall good examples being pretty legible. In fact, because the language only relies on those few characters, anything else you type becomes a comment. Linebreaks, whitespace, alphanum…

To me, that's still unreadable. While the intention of the code may be documented, it's pretty hard to understand if that "+" is really correct, or if that "". I can't even understand if a comment starts or terminates a particular piece of code.

BTW, how come there are dashes in the comment?

Post reply on HN