arendtio

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.

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

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.

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.

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

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.

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.

Can someone please explain the downvotes?

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.

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.

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

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

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.

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.

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...

> 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.

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?!?

Claude isn't that cheap anymore ;-)

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.

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.

The irony is that LLMs are, at their core, very much just applied math...

Do you know when they stopped and why?

EDIT - AI says:

Cursor seems to have intentionally dropped semantic/embedding-based codebase indexing. Their explanation is that newer coding agents are now good enough at searching repos directly. They can grep in parallel, inspect directories, read likely files, and refine the search themselves. Cursor says this now works as well or better for most cases. [1]

So the architecture shifted from something like “chunk → embed → vector DB → retrieve” to “local search index/ripgrep → agent explores.” There is still an index, but it’s a conventional local search index. No embeddings are involved in that retrieval path. [1]

The interesting part is that Cursor was still reporting a ~12.5% accuracy gain from semantic indexing in January 2026. [2] So this looks less like “semantic search never worked” and more like agentic search improving fast enough that the extra infrastructure stopped being worth it.

[1] https://forum.cursor.com/t/what-do-you-think-about-cursor-re...

[2] https://cursor.com/blog/secure-codebase-indexing

Yes, even my 2013 Haswell-based Arch Linux KDE Desktop feels more responsive than my M4 MacBook. And I think the MacBook has so much more power under the hood, but somehow the animation settings or whatever are just not that good.

To be completely fair, I use the Desktop via DisplayPort at 144 Hz, while the MacBook uses HDMI + USB-C, and I believe it's just at 60 Hz, which is also a factor, but I honestly think that this is not the primary reason.

Crashes?!? I've been using Conversations for a long time and can't remember any crashes. Something must be wrong with your setup.

For me, the bigger problem is that I was unable to get OMEMO + Apple Clients working properly. I think OMEMO 1 has some design flaws and hope that OMEMO 2 will fix those.

Can't all the countries that are hit by US tariffs try to lower the barriers to trading with each other? Not a quick fix, but a signal to the US that they are losing its position in the long term.

I wonder how many other websites are doing such stuff. Lately, KDE Plasma often shows me that audio is being played by Firefox, but no tab in Firefox has the speaker icon. So far, I have not found which page causes this issue (I don't use AliExpress).

I think the cookie layer is missing the point.

I mean, it should say something like, 'Sure thing, we don't just use cookies for our servers, but to track you through half the internet, to know exactly what you want even before you know it. Please feel free to accept it or piss off.'

I don't like those lawyers either, but they are not the primary problem. The problems are tracking systems that don't just track you across one website but across multiple sites, like those deployed by Google and Facebook. And since Cambridge Analytica, we know that those are not just hypothetical scenarios and that they actually have an impact on elections and where our society is heading.

I think that would limit its capabilities so much that it would be much easier for ad platforms to find ways to circumvent it.

Everybody here knows that SQLite is not production-ready and does not scale.

This is just proof that it can't be used in real-world applications.

SCNR

I like the idea.

I solved the issue by building an extra Android Launcher for the kids, where you can add apps and videos, but then you have the problem that you can't configure your own launcher on all tablets (e.g. Fire Tablets).