Muxup

Motivation Like most people, I've been playing with agents to see where they're helpful, where they're not, and what kind of workflows are a good match for me.

Thanks to the Debian 64-bit RISC-V port it's really easy to build a sysroot appropriate for cross-compiling Clang/LLVM and its separate test suite.

Quite some time ago I shared a script and methodology for performing a cross-architecture debootstrap in a rootless way.

Simple goal: take advantage of my home router's WireGuard support and have one of my external servers connect using this, and pass all traffic from a certain user through that interface.

Last month I wrote up a fairly long piece on per-query energy consumption of LLMs using the data from InferenceMAX (note: InferenceMAX has since been renamed to InferenceX).

shandbox is a simple Linux sandboxing script that serves my needs well.

How much energy is consumed when querying an LLM?

Although analysing performance by way of instruction counting has obvious limitations, it can be helpful (especially when combined with appropriate analysis scripts) to get rapid feedback on the impact of code generation changes or to explore hypotheses a…

Recently I jotted down some notes on LLM inference vs training costs for DeepSeek and I wanted to add on an additional datapoint for training cost based on the recently released Olmo3 models from the Allen Institute for AI ("Ai2").

I recently had reason to do a quick comparison of the performance of the Hetzner AX102 dedicated server and the high-end 'dedicated' CCX53 VPS on Hetzner Cloud and thought I may as well write up the results for posterity.