Model Internals, part 1: Proving LLM inference on Rust, CUDA, and Lean
Cartoon by JP Aumasson.
Badges come from GitHub once the author claims this feed.
Cartoon by JP Aumasson.
RLVR field notes · Security work · November 2026
GLP vectors hook one site: the residual stream after a layer’s writes have folded in.
Calif’s write-up on CVE-2026-86950, The Great Glyph Grift, by Dion Blazakis, Josh Maine and Anna Groza, is the kind of patch-analysis work I enjoy most: take a one-line advisory from Apple, “may have been exploited in an extremely sophisticated attack against specific targeted…