Hacker News: car

Model with metacognitive guidance identifies zero-click full-chain RCE in BlueZ

car — Wed, 30 Sep 2026 23:01:56 +0000

Article URL: https://twitter.com/autopoiesislab/status/2083221810171224416

Comments URL: https://news.ycombinator.com/item?id=49915595

Points: 2

# Comments: 0

New comment by car in "Eating Fruit Skins"

car — Sun, 13 Sep 2026 07:10:48 +0000

Marzipan

New comment by car in "Verschlimmbesserung: The Word Your Software Updates Need"

car — Sat, 29 Aug 2026 06:26:22 +0000

How about Verscheisserung / Verschisserung?

I do like the sound of Verscheissification.

As Picard said: Enshitify! (Apologies to my Trekkie friends.)

New comment by car in "Verschlimmbesserung: The Word Your Software Updates Need"

car — Fri, 28 Aug 2026 23:01:38 +0000

We've misunderestimated you.

New comment by car in "Qwen 3.8 27B is excellent, but it defaults to overthinking things"

car — Mon, 17 Aug 2026 10:54:26 +0000

If you are on Mac, have a look at the Llama-macOS app. They claim sensible settings for the linked model downloads. I'd expect the authors of Llama.cpp and the Huggingface folks to know this stuff.

https://news.ycombinator.com/item?id=49328008

New comment by car in "Llama-macOS – Agentic and MCP Native macOS Front End for Llama.cpp"

car — Mon, 17 Aug 2026 08:49:31 +0000

If you have llama.cpp installed, Llama uses it. Otherwise, it installs a prebuilt binary for your Mac. Models you've already installed via llama.cpp show up in the app automatically. You can install any GGUF model from Hugging Face, and Llama also recommends models that fit your Mac's hardware.

You can chat with any model in the built-in WebUI, connect other apps (coding agents, chat UIs, editors), or use the API directly. Models load when requested and unload when idle, so they don't take up memory when not in use.

> Features

- 100% local — Models run on your Mac; no data ever leaves it

- Small footprint — 4 MB native macOS app

- Zero configuration — models are auto-configured with optimal settings for your Mac

- Model recommendations — a built-in list of models your Mac can run, installable in one click

- Standard storage — models live in the Hugging Face cache, shared with llama.cpp and other tools

- Built on llama.cpp — from the GGML org, developed alongside llama.cpp

> Installation

To install llama.cpp , run:

  brew install llama.cpp

To install llama-app, run:

  brew install --cask llama-app

Llama-macOS – Agentic and MCP Native macOS Front End for Llama.cpp

car — Mon, 17 Aug 2026 08:49:31 +0000

Article URL: https://github.com/ggml-org/Llama-macOS

Comments URL: https://news.ycombinator.com/item?id=49328008

Points: 6

# Comments: 2

Conversion of CO2 to CO by Solvated Electrons in Molten Salts

car — Sun, 16 Aug 2026 23:59:45 +0000

Article URL: https://pubs.acs.org/aelccp/article/11/8/5297/5243806/

Comments URL: https://news.ycombinator.com/item?id=49325066

Points: 4

# Comments: 1

New comment by car in "llama.cpp"

car — Wed, 12 Aug 2026 09:04:34 +0000

This MacOS app used to be called LlamaBarn. Really excellent to see the fast progress being made.

Official repo, also has documentation how to configure server parameters:

https://github.com/ggml-org/Llama-macOS

Small tip, install llama.cpp with brew before llama.app, which will pick up the existing llama.cpp. That way it's easier to stay up to date with llama.cpp, since llama.app is on a slower release cadence.

Also, models installed with the hugging face CLI (hf) are picked up by llama.app automatically. The CLI will keep the model cache updated, e.g. when models get updated.

Llama.cpp became part of Huggingface recently.