Hacker News: terhechte

New comment by terhechte in "Flash-MoE: Running a 397B Parameter Model on a Laptop"

terhechte — Sun, 22 Mar 2026 16:49:51 +0000

Thank you for NeoVim! I also use it every day, mostly for thinking / text / markdown though these days.

Have you compared against MLX? Sometimes I’m getting much faster responses but it feels like the quality is worse (eg tool calls not working, etc)

New comment by terhechte in "Anthropic takes legal action against OpenCode"

terhechte — Thu, 19 Mar 2026 20:43:40 +0000

you can also use Claude Code programmatically with the `prompt` parameter in the cli.

New comment by terhechte in "OpenAI Has New Focus (on the IPO)"

terhechte — Thu, 19 Mar 2026 07:51:39 +0000

ChatGPT allows setting a "personality" profile Settings -> "Base style and tone". Try the "Efficient" setting. Its great. no emoji, no clickbait.

New comment by terhechte in "Nvidia NemoClaw"

terhechte — Wed, 18 Mar 2026 17:55:34 +0000

How is Peter "early in their career"? When he sold PSPDFKit for 100mio in 2020 he had been working on it for 13 years, and before that he'd worked as an engineer.

New comment by terhechte in "The engine of Germany's wealth is blocking its future"

terhechte — Mon, 09 Mar 2026 17:15:42 +0000

Any proof for this claim?

New comment by terhechte in "Agent Safehouse – macOS-native sandboxing for local agents"

terhechte — Mon, 09 Mar 2026 12:44:42 +0000

Shuru should do exactly what you want:

https://shuru.run

New comment by terhechte in "Step 3.5 Flash – Open-source foundation model, supports deep reasoning at speed"

terhechte — Thu, 19 Feb 2026 13:59:36 +0000

Did you try an MLX version of this model? In theory it should run a bit faster. I'm hesitant to download multiple versions though.

New comment by terhechte in "Gemini 3 Deep Think"

terhechte — Fri, 13 Feb 2026 02:06:51 +0000

so your definition of consciousness is having petty emotions?

New comment by terhechte in "Resizing windows on macOS Tahoe – the saga continues"

terhechte — Fri, 13 Feb 2026 02:02:25 +0000

I agree that macOS has become worse, however your examples don't really count:

Window snapping was implemented some time ago: https://www.macrumors.com/2024/06/12/macos-sequoia-window-ti...

Instead of win key, you can press F3, or just set a hotkey that works for you in the System Preferences

Instead of clicking the red maximize button, you can double-click the window header / title. This will use an algorithm to try to resize the window to the best size for its content.

New comment by terhechte in "Putting Gemini to Work in Chrome"

terhechte — Thu, 29 Jan 2026 07:48:39 +0000

I like doing side projects, I don't like wasting a day of work potential on any of these web apps: Google Cloud, AWS, Azure, Appstore Connect, Google's Android App Store, RevenueCat, Stripe, etc

I dread having to log in to these systems and waste hours achieving the simplest tasks.

This is what I'm using Claude for. E.g. I log in to AppStore connect, tell it what I need (3 subscription tiers), it will do all the clicking and editing and Apple's stupid UI, then I will ask it to create a summary for RevenueCat, and use another Claude session in there to click all the buttons to configure based on what just happened in Appstore connect.

Or configuring S3 buckets or whatnot.

New comment by terhechte in "Virtual Boy on TV with Intelligent Systems Video Boy"

terhechte — Wed, 28 Jan 2026 17:08:59 +0000

I tried a virtual boy the first time some months ago. I was super impressed with the quality of the graphics. I've used a Quest 3 and a Vision Pro and obviously these are very different beasts, but its just impressive that in terms of sharpness, this 90s device felt as good.

New comment by terhechte in "Fedora Asahi Remix is now working on Apple M3"

terhechte — Mon, 26 Jan 2026 22:22:03 +0000

KDE has a setting to switch the cmd & command keys so that e.g. command+c copies instead of ctrl+c. This works in all KDE apps (it will not work if you install any Gnome/GTK app, though). I forgot the setting but its something in advanced and used to be called Emacs key binds, but now I think it just refers to the keys.

Anyways, beyond that, have a look at Kinto which tries to do everything in one box, but it is an additional software you have to run:

https://github.com/rbreaves/kinto

New comment by terhechte in "Flux 2 Klein pure C inference"

terhechte — Sun, 18 Jan 2026 20:59:11 +0000

There're multiple task solutions for Claude or other llms that let it define tasks, add implementation notes and (crucially) add sub-tasks and dependencies. I'm using Beads (https://github.com/steveyegge/beads) and I think it really improves the outcome; especially for larger projects.

New comment by terhechte in "2026 will be my year of the Linux desktop"

terhechte — Sat, 03 Jan 2026 12:31:54 +0000

There's a mix of both worlds that I've tried for a while and want to pick up again in 2026: Use macOS so that I can utilize the great hardware and the well integrated drivers (e.g. sleep, performance, silence), but then for each project / work stream just fire up a lightweight linux VM fullscreen and do everything related there. E.g. all browser windows/tabs, apps, file explorer windows, terminal sessions. When I stop working I pause the VM. When I need to continue everything is as I left it. The main reason why I stopped was that the 2d hardware acceleration for Linux didn't work in UTM.app. I think I'll just need switch to Parallels or VMWare

New comment by terhechte in "1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5"

terhechte — Fri, 19 Dec 2025 16:34:03 +0000

Tim Cook is famous for locking in their prices years in advance.

New comment by terhechte in "Show HN: Learn Japanese contextually while browsing"

terhechte — Wed, 17 Dec 2025 07:34:20 +0000

Do you perchance have this on Github? I like the idea but would love it for another language, so would be interested in your add-on.

New comment by terhechte in "Why proteins fold and how GPUs help us fold"

terhechte — Mon, 15 Dec 2025 08:22:15 +0000

I don't know the space, so I found the article interesting. Please explain, what's wrong with it?

New comment by terhechte in "Qwen3-Omni-Flash-2025-12-01：a next-generation native multimodal large model"

terhechte — Wed, 10 Dec 2025 17:54:43 +0000

Is there a way to run these Omni models on a Macbook quantized via GGUF or MLX? I know I can run it in LMStudio or Llama.cpp but they don't have streaming microphone support or streaming webcam support.

Qwen usually provides example code in Python that requires Cuda and a non-quantized model. I wonder if there is by now a good open source project to support this use case?

New comment by terhechte in "CachyOS: Fast and Customizable Linux Distribution"

terhechte — Sun, 30 Nov 2025 19:01:34 +0000

I oftentimes run Linux Desktop fullscreen in a VM on macOS. macOS acts like a hardware abstraction layer in that case. Depending on the task and the tools, I sometimes prefer this option (I do like the macOS UI though (except for the current version), I just like to use the right tool for the job)

New comment by terhechte in "CachyOS: Fast and Customizable Linux Distribution"

terhechte — Sun, 30 Nov 2025 11:34:19 +0000

I wish they had a working ARM port