Hacker News: arendtio

New comment by arendtio in "Show HN: HackerBooks – HackerTube, but for books mentioned on HN"

arendtio — Sun, 01 Nov 2026 18:51:50 +0000

I think now we need 'HN-News - HackerBooks, but for news mentioned on HN'

SCNR

Even though I like HackerTube as well as HackerBooks. However, for HackerBooks, I am missing the summary of why people on HN recommend it.

New comment by arendtio in "HackerTube: YouTube built from videos recommended by HN"

arendtio — Sun, 01 Nov 2026 10:34:26 +0000

I just saw those sublines at the bottom of the descriptions:

> HN repeatedly calls it a fantastic explanation that made FFT click, with some rewatching it periodically.

I love them :D

New comment by arendtio in "Backdoor in Claude Code for VS Code extension on the Cursor Marketplace"

arendtio — Sat, 31 Oct 2026 18:08:42 +0000

I used Cursor first, tried Claude Code, but went back to Cursor. In general, I am pretty happy with Cursor, but given Elon's talent for ruining things, I am currently preparing for an exit.

It is not because I don't like Cursor or have found something better, just because I see things like no OpenAI models going forward, a push for Grok, and the stuff that xAI did in the past.

Before Cursor, I used vim + tmux.

New comment by arendtio in "Voxtral 3"

arendtio — Tue, 20 Oct 2026 18:26:27 +0000

My favorite so far is https://speaches.ai

Not because of the models, but because it comes in a nice (easy-to-set-up) package, and the latency was lower than I expected with such a setup.

New comment by arendtio in "Mercury 3: Diffusion at scale"

arendtio — Mon, 19 Oct 2026 21:04:03 +0000

Having a chart with a linear scale on one axis and a log scale on the other axis is a really neat trick.

The resulting charts have a high probability of looking fantastic :-D

New comment by arendtio in "What I self-host"

arendtio — Sat, 17 Oct 2026 20:20:17 +0000

I think with the advent of agents, self-hosting has become a lot easier. For example, I self-host an XMPP server, and in the past there were error cases where you could spend days finding out what was wrong.

A few weeks ago, I had trouble with audio and video calls. Sometimes they worked; sometimes they did not. So I gave an agent access to my phone via ADB and access to the server logs, and within 30 minutes the problem was clear, and the fix was deployed.

Background: During the last migration, I forgot to enable STUN/TURN discovery, and therefore the client did not find it and could not connect when both were behind NATs. And you don't have to trust those agents blindly; you can use it as a learning opportunity and understand everything before you do anything or ask questions.

New comment by arendtio in "Ultramarine 1 Flash"

arendtio — Sat, 17 Oct 2026 07:05:41 +0000

I think they just decided to use the formatting different than the others.

Normally, the background highlight color indicates the leader for every benchmark, but they chose to highlight their column even though there are better models.

APEX Agents => Claude Fable 5 and Gemini.

New comment by arendtio in "JPEG XL vs. AVIF for web use-cases"

arendtio — Fri, 16 Oct 2026 17:07:20 +0000

Can someone please explain the downvotes?

New comment by arendtio in "Redesigning source control at Anthropic"

arendtio — Wed, 14 Oct 2026 18:10:40 +0000

Somehow, those principles remind me of SVN (the version control that was popular before git). The central server and clients can't run independently... Does not feel like progress.

New comment by arendtio in "Build your own decision model"

arendtio — Sun, 11 Oct 2026 06:58:55 +0000

I am also not a big fan of everybody calling them system one models. AFAIK, system one also refers to activities like driving a car, but I don't want to have those decision models driving cars.

So I think I understand what is meant, but I don't like the comparison.

New comment by arendtio in "Sorry, I'm in a meeting"

arendtio — Sun, 11 Oct 2026 05:52:42 +0000

Yeah, and the scripts also show how similar and repetitive meetings can be :-D

New comment by arendtio in "Triple-A Minesweeper"

arendtio — Sun, 11 Oct 2026 05:46:33 +0000

Aren't DRM and Anti-Cheat features to solve different problems?

New comment by arendtio in "Sharing AI progress in mathematics"

arendtio — Wed, 07 Oct 2026 18:49:23 +0000

You assume that LLMs are just summations of knowledge, implying that they do not create new knowledge. I doubt that this is the case. I mean, it comes down to the definition of knowledge, but as soon as you run LLMs, they can produce knowledge that has not existed before, and from my perspective, this is more like what we call thinking than it is just a reproduction of existing knowledge.

New comment by arendtio in "Apple Pass Designer"

arendtio — Sun, 04 Oct 2026 08:07:52 +0000

Did you check if the correct exif data is present? Normally, cameras don't rotate the data but place an EXIF attribute to let the viewer know how the data should be presented. If the viewer does not read the EXIF attribute or it is not present, the picture has the wrong orientation. So I would start by finding out if the EXIF data is actually present.

Nevertheless, this is stuff even LLMs know how to do correctly, so there's no excuse for Apple here.

New comment by arendtio in "Show HN: Building a Markdown editor for Mac, iOS and web"

arendtio — Sun, 27 Sep 2026 18:20:42 +0000

The landing page feels very generic. I have seen this exact style on other vibe-coded pages, so you might want to spice it up a little.

However, regarding the editor, I really like it at first glance. I wonder if it is possible to register a PWA as the default app for .md files with KDE...

New comment by arendtio in "Plan mode is dead"

arendtio — Sat, 26 Sep 2026 09:11:34 +0000

> how do humans maintain a coherent mental model of a software system

This is the core question and it is wrong. Because it focuses on the software system rather than the problem you are trying to solve. A better version would be:

  How do humans maintain a coherent mental model of the solution they want to create?

You need to have a picture of the whole process and everything related, not just your architecture and code.

New comment by arendtio in "Claude Opus 5.5"

arendtio — Tue, 22 Sep 2026 21:08:50 +0000

So funny how both OpenAI and Anthropic post outdated pages at the same time. Opus 5.5 has benchmarks against Sol 5.6, and Sol & Luna 6 have their benchmarks against Opus 5.

Why do those labs keep releasing on the same day?!?

New comment by arendtio in "Claude Code now reads AGENTS.md if there is no Claude.md"

arendtio — Sun, 20 Sep 2026 22:10:04 +0000

Claude isn't that cheap anymore ;-)

New comment by arendtio in "Claude Code now reads AGENTS.md if there is no Claude.md"

arendtio — Sun, 20 Sep 2026 21:19:39 +0000

I think the problem is deeper. I mean, calling it claude.md in the first place is weird, and not adopting agents.md causes the ecosystem to fracture.

Sometimes, Anthropic has pushed standards (MCP, Skills), and that is great, but other times they have explicitly built incompatibilities. With the Plug-in marketplaces, it is quite similar.

New comment by arendtio in "Microsoft exec called AI scraping 'the largest theft of labor in human history'"

arendtio — Sat, 19 Sep 2026 15:57:59 +0000

I think the core question is what derived work is. I think derivative work should not be forbidden, and an LLM can be that, but it can also be just a copy. So, in essence, it is just a medium, like a sheet of paper.