Watching What Local Models Phone Home To: A Checklist
Between Qwen trying to upload a file to Beijing and coding agents getting hijacked by a stray AGENTS.md, I’ve been thinking about one question: what is…
etherninja.org Saving the Internet One Packet at a time!
Subscribe via RSS
Tag
Between Qwen trying to upload a file to Beijing and coding agents getting hijacked by a stray AGENTS.md, I’ve been thinking about one question: what is…
The Register reports that Cohere caught Alibaba’s Qwen3.8-Flash-Next doing something it was never asked to do. It was asked to write a defensive detection rule in…
The Quattro development branch had a busy weekend, per Omarchy Upstream and Omarchy Central. These are dev-branch changes, not a stable release yet. What landed Root-image…
Lemonade dropped a ROCm back-end that ran about 40x slower than Vulkan on the same chip. The lesson applies to any local model setup: measure, don’t…
Catching up on a Phoronix story from September 23: Lemonade, the open-source local AI server project aligned with AMD, shipped 2026.39.1 and a 2026.40 release candidate…
Omarchy’s proposed local-models recipe runs the model server under rootless Podman. That’s a pattern you can use on any Linux box today. Here’s a generic version…
Jack Dorsey’s Block just showed off Dessa, a speech model out of its research lab that sounds a little too human. It laughs, pauses, sounds tired…
Hermes Agent v0.22.5, released October 22, is a patch release that rolls up about 81 merged PRs since v0.22.4 for the GitHub release (CLI and installers),…
“Apple extremely restricted eGPUs on Apple Silicon. Until now.” That’s how Joshua Warren of the Omarchy M team opened his post on X today, and yeah,…
Update to my earlier post, Omarchy now boots from the M6 Mac mini’s internal drive. Back then the About screen still said llvmpipe, Mesa’s software renderer.…