Daily digest for 2026-10-21 · 11 new stories (previously covered stories are never reposted)
eMudhra Intermediate CA CompromiseSimon Willison · 2026-10-20
eMudhra Intermediate CA Compromise This is very, very bad news: The private keys of eight eMudhra intermediate CA certificates have been compromised. They chain to roots trusted by the Mozilla, Microsoft, Apple and Chrome root programs and by many downstream trust stores. Any sof
Battle Drones - a vibe coded RTS with audio-based multiplayerSimon Willison · 2026-10-20
My latest vibe coded game experiment is a Command & Conquer style RTS (Real Time Strategy) game called Battle Drones ( play it here ). Unlike my previous experiments , this one is actually fun to play . I'm somewhat embarrassed to admit that I got there by telling Claude to "Make
b11796llama.cpp Releases · 2026-10-21
mtmd: add state object for mtmd_gen ( #30902 )
b11795llama.cpp Releases · 2026-10-21
server : forward llama.cpp sampling params on /v1/messages ( #30856 ) server : forward llama.cpp sampling params on /v1/messages server : pass the request through on /v1/messages instead of copying listed keys NIT: Change comment from multiline to single line server : accept llam
b11793llama.cpp Releases · 2026-10-21
llama : optimize vocabulary loading ( #30679 ) llama : optimize vocabulary loading Update src/unicode.h Co-authored-by: Georgi Gerganov
[email protected] CR : added reserve in gguf_kv_to_str CR : trailing space fix Co-authored-by: Georgi Gerganov
[email protected] Website: ht
v0.40.7Ollama Releases · 2026-10-21
What's Changed pplx-decider is a 27B decision model from Perplexity, fine-tuned from Qwen3.8-27B Continuing an OpenAI-compatible Responses conversation no longer fails when switching between models with and without thinking, or when the history contains another provider's compact
v0.40.7-rc1: mlx: deduplicate CUDA runtime payloads (#17956)Ollama Releases · 2026-10-20
Deduplicate MLX CUDA runtime payloads Move CUDA libraries shared by the GGML and MLX backends into the sibling CUDA payload, and teach in-process and subprocess MLX loading to resolve that packaged dependency directory. Keep MLX-private libraries and JIT headers in the MLX overla