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

71–80 of 97 posts

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

#71

Post by tessierashpool9 »

geon wrote: post #70
tessierashpool9 wrote: post #67

Earlier quoted context omitted.

I mean, isn't that a little ridiculous? Aren't those language models already solving complicated exam questions and mathematical problems?

According to the creators, the models are on a phd level of intelligence, but they can’t get the simplest thing right.

Overselling is only the tip of the iceberg. The real problem is that a lot of managers base their decision to introduce language models into business processes on cutting edge Pro edition demos, but what is, of course, actually used in production is some cheap Nano/Flash/Mini version.

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

#73

Post by Andrex »

ACCount37 wrote: post #49
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...

All LLMs are, it's an innate thing. Google just sucks at the kind of long context training you need to do to mitigate that.

I would bet they won't suck at it for much longer, Gemini's progress in undeniable.

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

#74

Post by ACCount37 »

Andrex wrote: post #73
ACCount37 wrote: post #49

Earlier quoted context omitted.

All LLMs are, it's an innate thing. Google just sucks at the kind of long context training you need to do to mitigate that.

I would bet they won't suck at it for much longer, Gemini's progress in undeniable.

It was a consistent weak point for Gemini, compared to other major AIs. Reportedly, still is.

The progress is undeniable, the performance only ever goes up, but I'm not sure if they ever did anything to address this type of deficiency specifically. As opposed to being carried upwards by spillover from other interventions.

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

#75

Post by brap »

Gemini is my favorite, but it does seem to be prone to “breaking” the flow of the conversation.

Sharing “system stuff” in its responses, responding to “system stuff”, starts sharing thoughts as responses, responses as thoughts, ignoring or forgetting things that were just said (like it’s suddenly invisible), bizarre formatting, switching languages for no reason, saying it will do something (like calling a tool) instead of doing it, getting into odd loops, etc.

I’m guessing it all has something to do with the textual representation of chat state and maybe it isn’t properly tuned to follow it. So it kinda breaks the mould but not in a good way, and there’s nothing downstream trying to correct it. I find myself having to regenerate responses pretty often just because Gemini didn’t want to play assistant anymore.

It seems like the flash models don’t suffer from this as much, but the pro models definitely do. The smarter the model to more it happens.

I call it “thinking itself to death”.

It’s gotten to a point where I often prefer fast and dumb models that will give me something very quickly, and I’ll just run it a few times to filter out bad answers, instead of using the slow and smart models that will often spend 10 minutes only to eventually get stuck beyond the fourth wall.

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

#76

Post by perching_aix »

drstewart wrote: post #64
hdgvhicv wrote: post #44

Earlier quoted context omitted.

Puritans were kicked out of Europe for their views

Nothing says tolerance and no censorship like kicking out people for their views

If people are tolerant, they're woke. If people are intolerant, they're nazis. Standards of conduct are oppressive, but the lack of them indicate a shithole. And of course, anything in-between is just performative fence-sitting.

Tough crowd over here. Cultural bankruptcy speedrun much?

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

#77

Post by Workaccount2 »

tessierashpool9 wrote: post #59

Asked for a solution of a photographed Ubongo puzzle: https://gemini.google.com/share/f2619eb3eaa1 Gemini Pro neither as is nor in Deep Research mode even got the number of pieces or relevant squares right. I didn't expect it to actually solve it. But I would have expected it to get the basics right and maybe hint that this is too difficult. Or pull up some solutions PDF, or some Python code to brute force search ...…

LLM's are bad at anything with images.

There is something fucky about tokenizing images that just isn't as clean as tokenizing text. It's clear that the problem isn't the model being too dumb, but rather that model is not able to actually "see" the image presented. It feels like a lower-performance model looks at the image, and then writes a text description of it for the "solver" model to work with.

To put it another way, the models can solve very high level text-based problems while struggling to solve even low level image problems - even if underneath both problems use a similar or even identical solving frameworks. If you have a choice between showing a model a graph or feeding it a list of (x,y) coordinates, go with the coordinates every time.

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

#78

Post by hdgvhicv »

drstewart wrote: post #64
hdgvhicv wrote: post #44

Earlier quoted context omitted.

Puritans were kicked out of Europe for their views

Nothing says tolerance and no censorship like kicking out people for their views

So European values of the 1500s through 1700s are not puritan values.

Europe has liberalised since then.

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

#79

Post by nottorp »

lawn wrote: post #25
codetiger wrote: post #12

Earlier quoted context omitted.

All of a sudden, internet is full of people who hate AI written articles. A few months back, my article got a lot of haters because I used AI tools to improve my draft. Being a non-english first language person, I don't see an issue. But I wish AI improves to an extend where draft to complete articles don't look AI written.

I also don't have English as my first language and I think it's a shitty excuse. Articles written by AI are soulless and shitty. Do yourself and the readers a favor and write yourself, even if it contains errors.

They sound like politician speak or corporate speak.

To the OP: do you like how your politicians sound in your native language? If not, don't let a LLM rewrite your article.

Btw, I'm not a native speaker either.

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

#80

Post by artyom »

I thought "The Data Scarcity Problem" from the article is very well known to us engineers?

It's where the pulleys of a very sophisticated statistical machine start to show, and the claims about intelligence start to crumble.

Reason AI is great for boilerplate (because it's been done a million times) and not so great for specifics (even if they're specifics in a popular language).

Post reply on HN