Catalogue record · hackernews
My toy kernel language now runs LLMs, every kernel compiled at runtime from Phobos. On a seven-year-old RTX 2080 SUPER it decodes as fast as llama.cpp or faster on all but two models I tried, including a 35B mixture of experts. Most of the
Seen on hackernews · last checked 2026-10-21.
The teardown — how it actually charges, which mechanism was found, and the seam worth taking — is in the daily letter. This page carries the record and the signals so search engines and link previews have something real to read; the judgement stays with the readers who asked for it.
Get the daily letterThe same record sits in the full catalogue, where every entry can be searched and filtered by the signals above.