Hacker News: yrds96

New comment by yrds96 in "Seedance 2.5"

yrds96 — Sun, 02 Aug 2026 02:04:55 +0000

The bicycle was improved a lot when it was created but did changed a little since then too

New comment by yrds96 in "Substack writers, you need a website"

yrds96 — Tue, 28 Jul 2026 17:39:42 +0000

Fediverse. We need to push Fediverse

New comment by yrds96 in "Htmx 4.0, the first JavaScript library to release exclusively on the Game Boy"

yrds96 — Mon, 27 Jul 2026 03:58:08 +0000

I don't see a relation in this. You can both use LLMs and care about your codebase design. Frameworks and libraries are still relevant, and each one has its tradeoffs.

New comment by yrds96 in "GigaToken: ~1000x faster Language model tokenization"

yrds96 — Thu, 23 Jul 2026 00:28:03 +0000

This can make a huge difference for local models on modest hardware

New comment by yrds96 in "Decoy Font"

yrds96 — Thu, 16 Jul 2026 18:09:19 +0000

Which sufficient tooling calls even OCR can read this, but I think this can be improved

New comment by yrds96 in "xAI is looking more like a datacentre REIT than a frontier lab"

yrds96 — Tue, 09 Jun 2026 23:50:28 +0000

I think Elon Musk realized that only hardware vendors are profiting. Even if AI doesn't make it, datacenters can be used for something else

New comment by yrds96 in "Zig by Example"

yrds96 — Mon, 08 Jun 2026 15:30:35 +0000

This is outdated and AI generated.

If you want a good source of zig learning material interactive and by examples please check out ziglings: https://codeberg.org/ziglings

It's writen and tested by humans, which is essential for learning purposes. It's listed in the official zig website, by the way.

This project is always up to date to the latest zig release.

New comment by yrds96 in "When AI Builds Itself: Our progress toward recursive self-improvement"

yrds96 — Fri, 05 Jun 2026 01:48:21 +0000

I can't still conceive the fact that a tool that only send/receive text from an external API consumes an absurd amount of RAM

New comment by yrds96 in "CAPTCHAs can still detect AI agents"

yrds96 — Fri, 29 May 2026 18:28:26 +0000

- LLMs can't learn, therefore, LLMs are only good for things on which they are trained. - Captchas are not friendly with trial and error, so agentic solutions also don't help. - It's impractical to train LLMs on everything. - We humans are capable of creating infinite ways of captchas.

While each of these sentences is true, captchas will always win against LLMs.

New comment by yrds96 in "An OpenAI model has disproved a central conjecture in discrete geometry"

yrds96 — Thu, 21 May 2026 07:24:42 +0000

There are a missing the context: The vibecoded application was written in python while the main code was written manually in C by Torvalds in this side project. He never ever said that AI produces better code than him in the language where he is proficientI.

New comment by yrds96 in "The vi family"

yrds96 — Wed, 13 May 2026 15:48:25 +0000

The LLM usage are disclosed only for the projects where this information is relevant.

By the way there are a lot of farmers that doesn't need the power of tractors to make farming their livehood. Makes sense when you realize that not everything needs to be super fast and efficient, sometimes cheap, slow and constant is enough.

New comment by yrds96 in "The vi family"

yrds96 — Wed, 13 May 2026 15:42:46 +0000

In Portuguese "vi" means "saw" (past of see) and vim means "came", the last one being source of many inside jokes in one of my first jobs

New comment by yrds96 in "Bun's experimental Rust rewrite hits 99.8% test compatibility on Linux x64 glibc"

yrds96 — Sat, 09 May 2026 22:33:48 +0000

Also passing tests doesn't mean something works.

Claude code C compiler passed 100% of gcc tests and couldn't even run a hello world...

New comment by yrds96 in "A desktop made for one"

yrds96 — Sun, 03 May 2026 21:07:50 +0000

The fact where all posts of this blog make sure to state that claude code is a life changer, i wouldn't doubt about it

New comment by yrds96 in "Anthropic Joins the Blender Development Fund as Corporate Patron"

yrds96 — Wed, 29 Apr 2026 01:49:51 +0000

It's clear that the beef Artists vs AI is clearly about genAI and not about other kind of AI

New comment by yrds96 in "Claude Pro: Opus model will only be available if extra usage is enabled"

yrds96 — Mon, 27 Apr 2026 22:13:17 +0000

Basically the title.

Anthropic is doing changes on their help support pages on what looks like it will be the next pricing change regarding how users will use Opus models on Pro Plan.

Claude Pro: Opus model will only be available if extra usage is enabled

yrds96 — Mon, 27 Apr 2026 22:13:17 +0000

Article URL: https://support.claude.com/en/articles/11940350-claude-code-model-configuration

Comments URL: https://news.ycombinator.com/item?id=47928088

Points: 70

# Comments: 31

New comment by yrds96 in "GitHub is having issues now"

yrds96 — Mon, 27 Apr 2026 19:21:07 +0000

I like the experience of exploring new repositories so I switched everything to codeberg which is where most of the projects I'm interested with are

New comment by yrds96 in "Amateur armed with ChatGPT solves an Erdős problem"

yrds96 — Sun, 26 Apr 2026 21:46:01 +0000

Yeah I was referring to the lack of comments on the website.

Thanks! That answer a lot and makes everything more interesting.

New comment by yrds96 in "Amateur armed with ChatGPT solves an Erdős problem"

yrds96 — Sun, 26 Apr 2026 06:25:41 +0000

Given by the fact that the problem is 60 year old, isn't there a chance this was indirect solved already and the model just crossed informations to figure out the problem?

By looking the website this problem was never discussed by humans. The last comments were about gpt discovering it. I was expecting older comments coming to a 60 year old problem.

Am I missing something?

Great discovery though, there might be problems like that same case that worth a try for a "gpt check"