HackerTrans
TopNewTrendsCommentsPastAskShowJobs

TeodorDyakov

no profile record

Submissions

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

teodordyakov.github.io
126 points·by TeodorDyakov·há 6 meses·90 comments

[untitled]

1 points·by TeodorDyakov·há 8 meses·0 comments

comments

TeodorDyakov
·há 6 meses·discuss
Tokenizationnnnnnn
TeodorDyakov
·há 6 meses·discuss
It is really funny to me that in 2026 a coherent, grammatically correct response is assumed to be written by an AI. Oh how the tables have turned.
TeodorDyakov
·há 6 meses·discuss
Gdpeval
TeodorDyakov
·há 6 meses·discuss
How conveniently you forgot about the most impotant things for a product to make money - marketing and the network effect....
TeodorDyakov
·há 6 meses·discuss
the world does not need more shitware. We need medical advances, scientific breakthroughs and societal shift to improve wellbeing of all people. these things are much harderthan writing shitty sofware and we will need not the current AGIs(Goggle Gemini 3 Pro and ChatGPT 5.2 Thinking) but ASI to solve them.
TeodorDyakov
·há 6 meses·discuss
If cars do not have agency how useful are they going to be. If the Internet does not have agency how useful is going to be. if fire has no agency (debatable) how useful is going be.
TeodorDyakov
·há 6 meses·discuss
DO you have any idea of the man hours it took to build those large projects you are speaking of? Lets take Linux for example. Suppose for the sake of argument that Claude Code with Opus 4.5 is as smart as an average person(AGI), but with the added benefit that he can work 24/7. Suppose now i have millions of dollars to burn and am running 1000 such instances on max plans. Now if I have started running this agent since the date Claude Opus 4.5 was released and i prompted him to create a commercial-grade multi-platform OS from the caliber of Linux. An estimate of the linux kernel is 100 million man hours of work. divide by 1000. We expect to have a functioning OS like Linux by 2058 from these calcualtions. How long has claude been released? 2 months.
TeodorDyakov
·há 6 meses·discuss
Why do you assume AGI needs to have agency?
TeodorDyakov
·há 6 meses·discuss
Claude Code With Opus 4.5
TeodorDyakov
·há 6 meses·discuss
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.
TeodorDyakov
·há 6 meses·discuss
I too noticed that Gemini is very reluctant to start spewing code directly, thats why I prompted it in such a specific manner to trigger the infinite loop. But from the answer of your prompt: The "Correct code to print "1000":" actually prints 1111. So yeah it is still wrong even for something super simple.
TeodorDyakov
·há 6 meses·discuss
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 '.'
TeodorDyakov
·há 6 meses·discuss
Visibilty - i have no idea if there are censoring algorithms at play anywhere.
TeodorDyakov
·há 7 meses·discuss
I think of it this way. If you dropped Einstein with a time machine two thousand year ago, people would think he is some crazy guy doing scribbles in the sand. No one would ever know how smart he is. The same is with people and advanced AGI like Gemini 3 Pro or Chatgpt 5.2 Pro. We are just dumber than them.
TeodorDyakov
·há 7 meses·discuss
That is extremely unlikely.
TeodorDyakov
·há 7 meses·discuss
I dream of a future where before any software is released we can predict 100 years into the future what effect it will have on every living thing and not release it if unhappiness delta for some living thing falls below a certain threshold.
TeodorDyakov
·há 7 meses·discuss
Where do stars live? Thats what I wonder.
TeodorDyakov
·há 7 meses·discuss
what is the use case. I did not read the page. Can you tell me where stars live?
TeodorDyakov
·há 7 meses·discuss
Hi. I am curious what was the benchmark question? Cheers!
TeodorDyakov
·há 8 meses·discuss
That was exactly my thought. Why automate the coding part to create something that will be used for coding (and in itself can be automated , going buy the same logic)? This makes zero sense.