Hacker News Reader

The interesting part is this:

"After losing a bunch of customers to Codex"

Hot take: Right now it's quite simple to loose customers, like customer churn from A to B or back. That's the weakest spot, isn't it? No matter how complex the products grown and how deep they are integrated into our systems, common users can easily switch. Even heavy users, I argue. Just tell Codex to rewrite the existing Claude-instructions into their own. Even that may not be necessary, if you organized your work "agent agnostic".

And I dont see how that could change, that's why they try to offer tools that are even more integrated into our lives. Like "dots". But this also narrows down the use cases and client base, I argue.

y42on Sonnet 5.5

When working with a whole bunch of sub-agents, like you probably would do when coding, 2-3 sessions at a time are probably not enough. Like I build very specific sub-agents for code review, ui review and so on. Within one project I work with at least 3 - 4 agents then. Using Opus on every task would not leave room for other everyday-tasks.

y42on Running local LLMs on your Mac: what fits, what's free, and what's overkill

good to have a quick overview, though I am missing some kind of depth, like

>There are others — MLX-native runtimes, llama.cpp directly — but Ollama and LM Studio cover 95% of people reading this.

Sure, but... MLX native runtime have a lot of advantages right? and they are not necessarily more complicated like eg ollama. It's worth to mention them, too.

Coming to the next missing part: use cases.

Running it locally competes with dozens of freely available chat bots. And for most simple parts, seriously, you don't need that sophisticated payed AI service. But then: how do local model's perform exactly here: let's start with coding, image generation and more? Like stuff that I probably really want to run locally.

y42on 'RAMageddon' hits consumer electronics as AI drains chip supply

I don't know.... With all those approaches to run AI in your own premise, people need their own hardware. It makes them independent. Of course hyperscalers and AI labs don't like that, but I argue that consumers prefer independence over some costs of operations. If this would be the case, people wouldn't own cars.

y42on OpenShot 4.0 – Open-source video editor

I am quite familiar with Resolve..I am not a pro, and it's probably totally overload for my purpose, but I think it's easy to learn and even quite intuitive

I tried many others, but mostly all others are not stable enough or have an even worse UI/UX... so I wonder... is this different?

y42on LinkedIn CringeBot 3000

No rockets, no emoticons? Not real LI cringe.

y42on Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

Dont want to crash the party here, but I am still sceptic about all those on-premise-llm-approaches.

I think we strongly need something like that (shameless plug, I tried to build something around bitNet for the same reason: https://github.com/nickyreinert/bitNetRTR).

But at the end, all aproaches I saw, however genius they are: the actual results are always a mess. It's a better chat buddy, nothing else. It's e.g. far away from an decent coding assistants. I fine tuned Gemma with domain specific knowledge. Running it on a 16GB VRM GForce. Even then it's okai'sh but far way from a mind blowing experience. I ran some of the promised open source model on my 36GB MBPro M3, in Pi, Hermes, Continue. Can't compare the results to what Claude or Codex are offering.

You need at least something that's far away from consumer hardware, like those 7k'ish GForce machines with 96GB VRAM to get an idea of a good competitive model.

But... please, proof me wrong! =)

y42on P2P local file transfer based on WebRTC

shameles self promotion: I posted similar thing a couple of days ago:

https://news.ycombinator.com/item?id=48773805

https://9.1-1-1.de

y42on German ruling declares Google liable for false answers in AI Overviews

the threshold is not low, I would argue, it's just companies like to exploit it.

(I just wrote an extensive analysis about that https://nickyreinert.de/2026/2026-05-28-google-maps-reviews/

y42on United Airlines 767 returns to Newark after Bluetooth name sparks alert

Security by Obviousness.

y42on Everything in C is undefined behavior

shameless plug, it's part of the Nerd Encyclopedia: it's also called "nasal demons".

https://nickyreinert.de/2023/2023-05-16-nerd-enzyklop%C3%A4d...

y42on Running local models on an M4 with 24GB memory

Having an M3 with 36 GByte I was under the assumption, that I can utilize like Qwen and similar models. It's quite easy to set up, you can use pi or hermes for CLI access, or "Continue" to use it in VS Code. You can choose between omlx, Ollama and even more to run the model itself. It's no rocket science, but the results are also not satisfying.

I use it occassionally for very easy tasks, fix typos or update meta data in blog posts. So yeah, it improves productivity. But coding-wise it's far away from Codex, Claude et al.

y42on A web page that shows you everything the browser told it without asking

Shameless plug: It's not that fancy but follows the same principle:

https://institut-fdh.de/?2026-aya

There's also this well known page which does the exact same thing in a more ordered way:

https://browserleaks.com/

y42on Poland is now among the 20 largest economies

First: if you compare rates (salary, wages,...) you also always must consider rents, cost of living etc.

Second: You can't just pick Berlin for comparison.

Third: Take away foreign owend companies from Berlin, you get a cheap, dirty poor capital.

y42on Ask HN: The death of software development as a job?

Most comments already explained it, however:

No! It's a common misunderstanding (imho) that software development is about "writing code" or knowing a programming language's syntax. It never was, it never will be. I experienced this misunderstanding:

I never studied CS or IT or anything related. All my skills are self taught, starting when I was a litle boy. When I was young, I had problems getting into this busines, because HR and recruiters where tasking me with "Write this <x> using this <y>". They wanted to see A grades from 6 years of a master in CS.

Well. I am not that guy that memorizes syntax or coding rules. My approach is very different - and so are many, I assume. And this is what software development is about: You get a problem and you find a way to solve it. At many stations in my professional career I was able to proof that. I "mastered" Pascal from the scratch, on the job. Same goes for VBA, Shell scripting, Python, PHP, JavaScript... you name it.

It may sound arrogant - but then you misunderstood what I am trying to say: The language, the syntax, the coding rules are just "tools" for me. I don't care what I use. I focus on the problem.

Isn't it the same as "Write this <x> using this <y>" you may ask? No. Because this expects a specific solution. Not saying this will not lead to a result. It just a very narrow view on the solution.

There are good software developers that can answer those questions "Write this <x> using this <y>". That's not the point. The point is: There are also great software developers who can't.

With AI you don't have to worry to memorize syntax or rules. You can focus on the problem solving process.

So, AI is changing how software will be created. It make it more efficient. And it changes how HR and recruites hopefully will look at this profession. It's not about A grades in a CS class.

y42on Higher usage limits for Claude and a compute deal with SpaceX

I want to believe. A couple of weeks ago I fell into this "trap", they offered a similar thing. I subscribed to the Pro Plan. Had fun for a couple of weeks and then I entered frustration phase. I love the product, but I hate those up and downs. My rant made it to HN front page - which I am not happy of. I want the stuff I build to be seen on the front page.

y42on Train Your Own LLM from Scratch

shameless plug:

A series of Jupyter notebooks explaining the whole machine learning mechanism, from the beginning

https://github.com/nickyreinert/DeepLearning-with-PyTorch-fr...

and of course also how to build an llm from scratch

https://github.com/nickyreinert/basic-llm-with-pytorch/blob/...

y42on Do_not_track

> The internet only took off because the primary business model which ran on ads and derivative information that servers do to their users.

quite the opposite I would argue:

https://nickyreinert.de/2020/2020-10-24-marketing-killed-the...

y42on Show HN: I remade my blog into a Windows 3.1 environment

That was the goal, yes (⌐■_■)

y42on I bought Friendster for $30k – Here's what I'm doing with it

I can't believe that domain trading is still a thing.. I am sitting on a bunch of "nice" domains; I could never imagine someone actually bought for not even vor 100 bucks... and here we are, 30k?

OK.

y42on Show HN: I remade my blog into a Windows 3.1 environment

reminds me of that:

https://institut-fdh.de/

but your's is way better implemented it seems - very nice!

(disclaimer: it's my site, shameless-plug)

y42on Show HN: Sig – personal & team knowledge base built from your work conversations

I like the clean style, I was working on something similar, but never reached that readines-level.

However, the first screen seems a little contra productive. User entered a paragraph and in return gets a "summary" - but it feels so long. It's probably okay... it just triggered me very first impulse.

And what remains unclear is the meaning of "Team Sync". What's happening there? Is it a "group chat" or does it sends messages?

Speaking of... what about integrations with like Teams, Slack, Discord? I know that Teams offers a Meeting Summary which would be great if you could directly store it in _sig_.

y42on I cancelled Claude: Token issues, declining quality, and poor support

I like your blog and I can totally relate to this article - it's like something I wanted to write about for a couple of weeks now. :D

https://thoughts.jock.pl/p/adhd-ai-agent-personal-experience...

y42on I cancelled Claude: Token issues, declining quality, and poor support

https://news.ycombinator.com/item?id=47894155

(I am just learning that "a couple of weeks" apparently means "2 weeks"...)

y42on I Cancelled Claude: Token Issues, Declining Quality, and Poor Support

I am trying Qwen3.5-9B-Claude-4.6 since a couple of days now locally coming from OMLX. Either via Hermes or Continue in VS Code. It's oka'ish, even performance-wise.

[1] https://huggingface.co/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-R...

y42on I Cancelled Claude: Token Issues, Declining Quality, and Poor Support

I dare to call meself a senior dev, so I don't need a replacement, I need a tool.

y42on I cancelled Claude: Token issues, declining quality, and poor support

That's what I am thinking, too. It sound's like a conspiracy theory, but at the end Anthropic et al benefits from models that don't finish their jobs. I recently read about this "over editing phenomenon". The machine is never done. It doesn't want to.

It's like dating apps. They don't want you to find a good match, because then you cancel the subscription.

y42on How to run Qwen 3.5 locally

> consumer-grade hardware

Not disagreeing per se, but a quick look at the installation instructions confirms what I assumed:

Yeah, you can run a highly quantized version on your 2020 Nvidia GPU. But:

- When inferencing, it occupies your "whole machine.". At least you have a modern interactive heating feature in your flat.

- You need to follow eleven-thousand nerdy steps to get it running; my mum is really looking forward to that.

- Not to mention the pain you went through installing Nvidia drivers; nothing my mum will ever manage in the near future.

... and all this to get something that merely competes with Haiku.

Don't get me wrong - I am exaggerating, I know. It's important to have competition and the opportunity to run "AI" on your own metal. But this reminds me of the early days of smartphones and my old XDA Neo. Sure, it was damn smart, and I remember all those jealous faces because of my "device from the future." But oh boy, it was also a PITA maintaining it.

Here we are now. Running AI locally is a sneak peek into the future. But as long as you need a CS degree and hardware worth a small car to achieve reasonable results, it's far from mainstream. Therefore, "consumer-grade hardware" sounds like a euphemism here.

I like how we nerds are living in our buble celebrating this stuff while 99% of mankind still doomscroll through facebook and laughing at (now AI generated) brain rot.

(No offense (ʘ‿ʘ)╯)

y42on How will OpenAI compete?

Why would you want to move conversations with you? I use multiple different models, I don't care about the history.

My "brain" in terms of projects, is local on my computer. I have a simple set of system rules that I need to copy.

I am not everyone, I understand that. What I try to say: don't overestimate the lock in effect of AI. I doubt there is one.

y42on Show HN: Cc-md – Zero-cost Obsidian sync across iPhone, Mac, and GitHub

Can you explain how you achieved it? I don't find it in your repo, I am too tired probably? However, I tried something different but stuck eventually with the receiving part on Android. One cannot just pull files from somewhere and put them into the Obsidian folder. I mean, not without efforts.