Hacker News: newswasboring

New comment by newswasboring in "Googlebook"

newswasboring — Wed, 13 May 2026 06:24:12 +0000

> I can imagine lots of cases where people with specific needs

You know, everyone used to have specific needs in clothing when I was young. Somehow fast fashion advertised that out of us to solve their own supply chain problems.

New comment by newswasboring in "Zig → Rust porting guide"

newswasboring — Tue, 05 May 2026 11:41:05 +0000

So is JavaScript haha.

New comment by newswasboring in "Ask HN: Who is using OpenClaw?"

newswasboring — Wed, 15 Apr 2026 22:31:56 +0000

I don't use openclaw but I spent few weeks on nanobot and then this week switched to Hermes. I have simple usecases like a news brief in the morning on my areas of interest, checking my email for latest updates on things I care about right now etc.

But I gave my wife access to the discord server, she burned 20% of weekly quota for codex (I use it as the provider) but created a skill which helps her practice dutch her way (she's learning it at A2 level for now). I went through the chats with her when she was showing it to me and it's amazing. She is a non technical person but she has tons of experience developing products. It was amazing (and to be frank very sexy) to see her work pretending as if she has been assigned a junior developer. The whole things a tangled mess of cron jobs, skills and scripts but her point is very simple "it maps perfectly to my learning style and keeps it fresher than flashcards or Duolingo".

Edit: wording. Also she wants me to mention at the end of the lesson it also does roleplaying which no other product gave her.

New comment by newswasboring in "Tell HN: OpenAI silently removed Study Mode from ChatGPT"

newswasboring — Sun, 12 Apr 2026 14:52:02 +0000

Does this work? I've been doing that for some weeks now, nothing has changed about my home page.

New comment by newswasboring in "Meta and TikTok let harmful content rise to drove engagement, say whistleblowers"

newswasboring — Wed, 18 Mar 2026 10:42:42 +0000

It's easy, let's start with banning 1. Obvious incitement of violence. If they can enforce just that much it would be great.

New comment by newswasboring in "Mistral AI Releases Forge"

newswasboring — Wed, 18 Mar 2026 10:41:34 +0000

To me it's obvious because the size of companies they are targeting (ASML being an obvious one). I think golf course marketing works well in the EU context when decisions are being made not purely on tech reasons.

New comment by newswasboring in "Mistral AI Releases Forge"

newswasboring — Wed, 18 Mar 2026 09:57:39 +0000

I have a general impression they are not interested too much in individual devs and making it suite their workflow. They want to be a B2B company and deliver a custom workflow per company.

Or it can just be a Google like problem where a big company one part doesn't talk to the other.

New comment by newswasboring in "Meta and TikTok let harmful content rise to drove engagement, say whistleblowers"

newswasboring — Tue, 17 Mar 2026 23:07:20 +0000

I'm sorry but are you saying it's hard to figure out what to do so let's do nothing? Banning racist and sexist content is not a slippery slope. It's just banning racist and sexist content, slope is only slippery because the salivating mouths of these social platforms grease them.

Also, I don't think people are advocating censorship, they are advocating not promoting assholes. You can have your little blog and be racist on it all you want, but let's not give these people equivalent of nukes for communication.

New comment by newswasboring in "Polymarket gamblers threaten to kill me over Iran missile story"

newswasboring — Mon, 16 Mar 2026 21:06:12 +0000

Yeah but we can see right through all that lawyer bullshit right? Gambling markets like polymarket are morally corrupt and we having given them too much space in our society already.

New comment by newswasboring in "Apideck CLI – An AI-agent interface with much lower context consumption than MCP"

newswasboring — Mon, 16 Mar 2026 18:35:03 +0000

I think big companies already protect against random commands causing damage. Work laptops are tightly controlled for both networking and software.

New comment by newswasboring in "Italian prosecutors seek trial for Amazon, 4 execs in alleged $1.4B tax evasion"

newswasboring — Thu, 12 Mar 2026 18:57:46 +0000

Taxes dont get deducted from people's salaries?

New comment by newswasboring in "Many SWE-bench-Passing PRs would not be merged"

newswasboring — Thu, 12 Mar 2026 13:49:24 +0000

Openspec does this. But instead of "?" it has a separate Open Questions section in the design document. In codex cli, if you first go in plan mode it will ask you open questions before it proceeds with the rest.

The UX is there, for small things it does work for me, but there is still something left for LLMs to truly capture major issues.

New comment by newswasboring in "Many SWE-bench-Passing PRs would not be merged"

newswasboring — Thu, 12 Mar 2026 10:34:45 +0000

I have a stupid solution for this which is working wonders. It does not help to tell the LLM "don't do this pattern". I literally make it write a regex based test which looks for that pattern and fails the test.

For example I am developing a game using GDscript, LLMs (including codex and claude) keep making scripts with no classnames and then loading them with @preload. Hate this, and its explicitly mentioned in my godot-development skill. What agents can't stand is a failing test. Feels a bit like enforcing rules automatically.

This is a stupid idea but it works wonders on giving taste to my LLM. I wonder if I should open source that test suite for other agentic developers.

New comment by newswasboring in "How to run Qwen 3.5 locally"

newswasboring — Sun, 08 Mar 2026 13:28:09 +0000

I think it's the same instinct as making your own Game Engine. You start off either because you want to learn how they work or because you think your game is special and needs its own engine. Usually, it's a combination of both.

New comment by newswasboring in "Ars Technica fires reporter after AI controversy involving fabricated quotes"

newswasboring — Wed, 04 Mar 2026 13:07:04 +0000

Things are more nuanced than agreeing and disagreeing. If you can't see that then...

New comment by newswasboring in "Claude's Cycles [pdf]"

newswasboring — Wed, 04 Mar 2026 13:05:09 +0000

> The prompt is unique but the tokens aren't.

The tokens aren't unique, but the sequence is. Every input this model sees in unique. Even tokens are not as simple as they seem

If you type "ejst os th xspitsl of fermaby?" in ChatGPT it responds with

> It looks like you typed “ejst os th xspitsl of fermaby?”, which seems like a garbled version of:

> "What is the capital of Germany?”

> The capital of Germany is Berlin.

> If you meant to ask something else, feel free to clarify!"

edit: formatting

New comment by newswasboring in "Ars Technica fires reporter after AI controversy involving fabricated quotes"

newswasboring — Tue, 03 Mar 2026 20:33:42 +0000

The original author clarified and you are still stuck here? Take a step back dude it's not that serious.

New comment by newswasboring in "Ars Technica fires reporter after AI controversy involving fabricated quotes"

newswasboring — Tue, 03 Mar 2026 16:44:20 +0000

> Junior was said specifically.

Yes, but I think you are taking this phrase more literally than its meant to be read.

New comment by newswasboring in "Ars Technica fires reporter after AI controversy involving fabricated quotes"

newswasboring — Tue, 03 Mar 2026 16:31:01 +0000

Even a senior dev being able to unilaterally delete your prod entirely should not be possible.

But I don't think the intention was to compare with junior devs, its just a popular shorthand for "your process sucks".

New comment by newswasboring in "I'm losing the SEO battle for my own open source project"

newswasboring — Tue, 03 Mar 2026 15:24:19 +0000

I fell for this yesterday, but for zeroclaw not nanoclaw. I found this website[1] through brave search I think. I was not paying too much attention as I was under the influence, it points to the wrong repo[2] and instructions install from that. I didn't like zeroclaw anyways so I tried to uninstall it and only then realized i'm on a forked repo.

[1] https://zeroclaw.net/ [2] https://github.com/openagen/zeroclaw