Hacker News: pixlmint

New comment by pixlmint in "MCP was always a bad idea?"

pixlmint — Mon, 21 Sep 2026 13:29:54 +0000

If not even OpenAI can properly box in their models I definitely won't trust myself to do so with the very limited time available to me, and instead just use a standard that's already defined, and proven to work.

New comment by pixlmint in "MCP was always a bad idea?"

pixlmint — Mon, 21 Sep 2026 07:16:31 +0000

What if I don't want my agent to have terminal access though? I get the feeling many people here simply never worked with smaller models, those will confuse cli args really quickly once context expands, and then you have no idea what damage they might do. With MCP's, they get just the access they actually need. Is the Principle of least privilege just not something we want to apply anymore?

New comment by pixlmint in "Feature Request: Support AGENTS.md"

pixlmint — Thu, 20 Aug 2026 06:12:44 +0000

yeh i tried pi, as a neovim user i naturally like customizability, but with how little i use agents, i want something that just works, which opencode does for me.

New comment by pixlmint in "OpenRouter is joining Stripe"

pixlmint — Thu, 20 Aug 2026 05:50:42 +0000

How is that a problem that's unique to openrouter? Who's to say when I query the Anthropic API directly, wanting to use Opus, but they determine it doesn' need Opus, route it to Sonnet instead and pocket the difference? The only difference with openrouter is that it's another layer where this type of fraud could occur.

New comment by pixlmint in "Zed DeltaDB"

pixlmint — Thu, 06 Aug 2026 10:37:14 +0000

this type of sh*t is why i'm glad i didn't switch from neovim to zed

New comment by pixlmint in "“Gravity is worth asking about”"

pixlmint — Wed, 05 Aug 2026 10:41:24 +0000

this is a discussion we often have where I work, where we're debating removing a feature due to difficulties maintaining it and few people needing it. I usually fight to keep it, with the argument "we aren't doing it for the people that don't need it, but for the ones that do." But at the end of the day, I'm not the one who has to pay for it.

New comment by pixlmint in "We finally learned to center a div, then browsers added sidebars"

pixlmint — Wed, 05 Aug 2026 09:01:16 +0000

I think it' very debatable whether or not this should be a web page's behaviour.

New comment by pixlmint in "AI fuels more than half of cybercrime in Africa as scams surge – Interpol"

pixlmint — Wed, 05 Aug 2026 08:40:53 +0000

remember, this is the worst AI is going to be...

New comment by pixlmint in "Pi's Minimalism Is Its Advantage"

pixlmint — Wed, 05 Aug 2026 07:37:02 +0000

that website is horrendous to look at on an eink display btw

New comment by pixlmint in ""Clean" Code, Horrible Performance (2023)"

pixlmint — Tue, 04 Aug 2026 18:50:27 +0000

you realize reading books isn't a zero-sum game right? I can still read more books, it didn't end with Clean Code

New comment by pixlmint in ""Clean" Code, Horrible Performance (2023)"

pixlmint — Tue, 04 Aug 2026 14:56:27 +0000

eh, when I read it as a newbie it was really helpful. still had to make my own experiences and judgments, but overall I think reading it made me a better programmer

New comment by pixlmint in "AI-Generated Images Discourage Me from Reading Your Blog"

pixlmint — Tue, 04 Aug 2026 13:47:59 +0000

Couldn't agree more - down to the shitty ms paint recommendation

New comment by pixlmint in "Taylor Farms has rewritten its cyclospora statement four times in sixteen days"

pixlmint — Mon, 03 Aug 2026 16:31:20 +0000

Started out with "It's not X, it's also Y", followed by an em-dash. I didn't read any further than that.

New comment by pixlmint in "LLM Usage in Debian: Three Proposals"

pixlmint — Sun, 26 Jul 2026 09:26:22 +0000

A is good, it's grounded. C is just based

New comment by pixlmint in "Judge approves $1.5B Anthropic settlement for pirated books used to train Claude"

pixlmint — Wed, 22 Jul 2026 09:14:36 +0000

if they had any intention of doing things "the right way", they would have gone to every publisher individually and asked for a proper license.

New comment by pixlmint in "Late.sh – a command-line Clubhouse for computer people"

pixlmint — Wed, 22 Jul 2026 09:11:56 +0000

yeah I was gonna say, it's very difficult to read on an eink display. And while we're at it, I believe my phone is set to reduced animations, which I believe is a preference that's exposed to websites, the experience would be much better without so much blinking going on.

New comment by pixlmint in "Advertise in ChatGPT"

pixlmint — Wed, 22 Jul 2026 08:02:00 +0000

They'll simply copy Google's playbook. First, clearly highlighted as advertisement results, usually the first three, so just with muscle memory you'll scroll down right away. Then they get bigger. Then the highlighting gets removed. Then it's just a tiny badge saying "advertisement".

New comment by pixlmint in "Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA"

pixlmint — Wed, 22 Jul 2026 05:49:44 +0000

didn't read the article, but just the title felt fishy because of course an inference provider wouldn't mind claiming to provide access to a mythos-class model. So far, GLM 5.2 is still my go-to, even at less than a third the parameter count compared to Kimi K3

New comment by pixlmint in "Kimi K3: Open Frontier Intelligence"

pixlmint — Fri, 17 Jul 2026 09:17:43 +0000

Crazy how mighty GLM-5.2 is at less than a third the parameter count. Z.ai really cooked with that one.

New comment by pixlmint in "Control the Ideas, Not the Code"

pixlmint — Tue, 14 Jul 2026 07:11:37 +0000

And if you had to email someone in Italian, would you really do it with poor grammar? Or would you write it in English and translate it, or use a tool to ensure it's correct?

I'm not telling him to stop writing on his own and instead just let AI write for him, but there's no shame in letting an NLP tool do what it's made for and correct the mistakes you made writing in a language you aren't native to.