Hacker News: yrds96

New comment by yrds96 in "Your codebase doesn't care how it got written"

yrds96 — Wed, 15 Apr 2026 06:28:18 +0000

Not sure what to think about the first part, but what you said about writing style, I think it's still reasonable to judge developers/engineers by writing style:

- Writing style does reveal how people understand problems and their approach for solving them. People that prioritize direct solutions over complex abstractions are still valuable to catch over engineered code.

- People with "good taste" in code can catch when AI generated code takes shortcuts to accomplish a certain task, this happens every day and we can't ignore it.

The state of AI code can be way better by 6 months or 1 year, or even more (we don't really know), but we're not there yet, and we can't wait until there to hire new people without considering those points.

New comment by yrds96 in "Great at gaming? US air traffic control wants you to apply"

yrds96 — Sat, 11 Apr 2026 06:41:05 +0000

Which tools do we have capable of automating it? LLMs? Not a good idea to put a machine that hallucinate 10% of the time in charge of human lives

New comment by yrds96 in "AI assistance when contributing to the Linux kernel"

yrds96 — Sat, 11 Apr 2026 06:30:05 +0000

AI tools can do the entire job from finding the problem, implementing and testing it.

It's different from the regular single purpose static tools.

New comment by yrds96 in "ChatGPT Pro now starts at $100/month"

yrds96 — Fri, 10 Apr 2026 01:24:12 +0000

I don't think people paying for AI at this moment are concerned about moral or ethics.

New comment by yrds96 in "System Card: Claude Mythos Preview [pdf]"

yrds96 — Tue, 07 Apr 2026 19:51:39 +0000

I think there's no SOA advance on this one worthy of "freaking out".

Looks like they just built a way larger model, with the same quirks than Claude 4. Seems like a super expensive "Claude 4.7" model.

I have no doubts that Google and OpenAI already done that for internal (or even government) usage.

Visual reasoning benchmark based on Analog Clocks

yrds96 — Sun, 29 Mar 2026 20:27:24 +0000

Article URL: https://clockbench.ai/

Comments URL: https://news.ycombinator.com/item?id=47566932

Points: 3

# Comments: 0

New comment by yrds96 in "Arm AGI CPU"

yrds96 — Sat, 28 Mar 2026 01:31:11 +0000

People ruined the word AGI before this to be fair, we will need another word to describe "real AGI" when it comes

New comment by yrds96 in "Schedule tasks on the web"

yrds96 — Fri, 27 Mar 2026 23:50:41 +0000

I'm using Opus on Claude Code and even on easy tasks, if you not review the changes properly, it creates tech debts. One of the most common issues is replicating the same logic with variables with different names (which makes grep harder to detect on future changes) in multiple places and lack of following project patterns. Even having a lot of .md files instructing to do the opposite. I still didn't find a workflow without human interaction that can be that efficient and reliable.

New comment by yrds96 in "DoorDash Tasks"

yrds96 — Sun, 22 Mar 2026 19:10:15 +0000

You should be concerned and not excited. This future might be near than we can imagine and we're just accelerating things without thinking about the consequences.

New comment by yrds96 in "Get Shit Done: A meta-prompting, context engineering and spec-driven dev system"

yrds96 — Thu, 19 Mar 2026 07:02:45 +0000

Let me guess. Yeat another bunch of md files trying to fix bad prompts from unskilled programmers?

New comment by yrds96 in "What 81,000 people want from AI"

yrds96 — Thu, 19 Mar 2026 06:47:01 +0000

For me it's so unrelevant reading about how a product is useful on the company itself website. This is at most marketing disguised as research.

New comment by yrds96 in "What 81,000 people want from AI"

yrds96 — Thu, 19 Mar 2026 06:42:44 +0000

Thanks. My galaxy s23 can't handle this website

Googling on Brazil about "Gemini said" shows unrevised content from Gemini

yrds96 — Thu, 19 Feb 2026 20:26:58 +0000

The phrase "O Gemini disse" (Portuguese for "Gemini Said") also works, but some times it's from someone that is genuinely paraphrasing Gemini responses.

But searching it in English makes everything more evident, since the phrase starts in English and then suddenly changes it to Portuguese.

I found even a digital news website doing it: https://cenariomt.com.br/mato-grosso/gemini-said-rondonopolis-mobiliza-pit-stop-contra-exploracao-sexual-e-trabalho-infantil-no-carnaval/

I wasn't the one that found out about "Gemini said" text being added when you copy the model response, but I decided to google about it to discover more, and ended up finding those kind of results. I tested on my computer, with Firefox and Chromium on Linux and couldn't reproduce this, so I believe this is something related to Chrome or Windows, since my girlfriend discovered it.

My guess is you use the equivalent of "Gemini said" in other languages too, you might find similar results.

Comments URL: https://news.ycombinator.com/item?id=47078774

Points: 3

# Comments: 1

New comment by yrds96 in "Magnus Carlsen Wins the Freestyle (Chess960) World Championship"

yrds96 — Mon, 16 Feb 2026 08:12:03 +0000

Yeah, it's hard to maintain physical performance as we are more susceptible to injuries which keeps us away from constant training, but our brain doesn't suffer by injuries, what allow us to go further. I think what makes people to drop at advanced age on "non-physical sports" it's to focus on other aspects of life over the sport because it's exaustive, if not impossible, to focus on both.

New comment by yrds96 in "IBM tripling entry-level jobs after finding the limits of AI adoption"

yrds96 — Sun, 15 Feb 2026 02:51:19 +0000

I'm not doubting of you or anything, but you just proved point above by saying you have a successful project without even mentioning which project is that.

New comment by yrds96 in "ai;dr"

yrds96 — Thu, 12 Feb 2026 21:22:15 +0000

Good article. Nothing is more frustate than reading a text that I don't even know if the person who "wrote" it, actually read it.

If someone wants to me read a giant text generated by a small and poor prompt, I don't wanna read it

If someone wants to fix that by increasing the effort and do a better prompt and express better the ideas, I rather read that prompt over the llm output

New comment by yrds96 in "Jellyfin LLM/"AI" Development Policy"

yrds96 — Thu, 29 Jan 2026 01:54:28 +0000

The effort to write shitty code is way less when you are using IA, you can create a 1k lines PR with a single prompt. This policy is important because no one is saying "we hate AI" but instead advises developers to use it with responsibility. This is coming in time since many people are using it without understanding problems and not being accountable regarding the contributions.

New comment by yrds96 in "I am a programmer, not a rubber-stamp that approves Copilot generated code"

yrds96 — Wed, 15 Oct 2025 06:24:10 +0000

Did people force React? Cloud infrastructure? Microservices? You get it.

I know there are people still using PHP 5 and deploying via FTP, but most people moved on to be better professionals and use better tools. Many people are doing this to AI, too, me included.

The problem is that some big companies and influential people treat AI as a silver bullet and convince investors and customers to think the same way. These people aren't thinking about how much AI can help people be productive. They are just thinking about how much revenue it can give until the bubble pops.

New comment by yrds96 in "Want to piss off your IT department? Are the links not malicious looking enough?"

yrds96 — Fri, 19 Sep 2025 04:21:11 +0000

Rickrolling doesn't feel the same with this bunch of ads. Sadly

New comment by yrds96 in "The GitHub website is slow on Safari"

yrds96 — Wed, 27 Aug 2025 14:32:25 +0000

Isn't the opposite? No one in this thread even cogitating how bad Safari is in terms of performance and supporting web standards? There's in one even partially blaming both. Github isn't the best example of a fast website, but if you can run it in Chrome and Firefox, even on rudimentary browsers like Palemoon (I tested) on decent hardware (even mobile), there's something clearly wrong on Safari.