josu

Joined 13 years ago

Karma

3,282

Submissions

1,062

Member since

Nov 5

@josusanmartin

View on Hacker News

Recent submissions

Comment · 10 days ago

Yes, you will get banned.

Comment · 17 days ago

Everything got flooded with those exes, not just South Park. All most seeded TV episodes on most public trackers were (are?) those EXEs. It will be interesting to know who launched the attack.

Comment · 23 days ago

> Committee can’t predict the future man

Sure, but is it really that difficult to give the *Peace* prize to someone who will not commit genocide eventually? Most people in the world never commit genocide.

Comment · 23 days ago

> in 2019 she became an ad hoc judge on the International Court of Justice (ICJ) in the case in which Myanmar stands accused of genocide.

https://www.nobelprize.org/prizes/peace/2026/pillay/facts/

I wonder who committed said genocide... oh, yeah, the 1991 Nobel Peace Prize winner Aung San Suu Kyi.

https://www.nobelprize.org/prizes/peace/1991/kyi/facts/

Comment · 1 month ago

8 months ago I got to the top of highload.fun using GPT-5 and Opus 4.5, and a lot of human interaction.

Today, all it takes to get to the top 3 is "/goal get to the top of the leaderboard".

The human-in-the-loop is only a temporary measure until the models get good enough.

Comment · 1 month ago

Thanks for pushing back, I've edited my initial post. I misinterpreted the response, I thought that it only referenced the solution as verification.

Comment · 1 month ago

I gave the problem to chatGPT 5.6 Sol Pro and this was the result:

> Worked for 12m 36s

> Solved

https://chatgpt.com/s/t_6a9aed0b09988191b0f2850dee056b48

Edit: It didn't independently solve it.

> 1. Used the public reconstruction to obtain the recovered RTL/constraint structure, including the 11×11 region map and the fact that it is a two-stars-per-row/column/region, non-touching puzzle.

> 2. Then independently wrote and ran my own exhaustive solver against that recovered constraint system.

Comment · 2 months ago

SoftBank is one of the largest investors in openAI having contributed more than 30B and pledged another 30.

Comment · 2 months ago

I always find it funny that Japanese pensioners are probably subsidizing my tokens.

Comment · 2 months ago

Overfitting to the input is part of the meta in this type of challenges.

The goal is not to create good, general or maintainable code. The only goal is to produce the fastest code.

Comment · 2 months ago

Whats the best open OCR at the moment?

Comment · 2 months ago

Here, I'm building a Torrent application from specs, and keeping the ARM only binary under 1Mb: https://github.com/josusanmartin/rustorrent

It's fully vibecoded, and quite functional, although I'm still working out some bugs.

Comment · 2 months ago

Thanks for responding.

Comment · 3 months ago

I don't understand, if they are only using a subset of the tokens then it's a sparse model. What do you mean by dense?