Daily digest for 2026-10-18 · 7 new stories (previously covered stories are never reposted)
Inline rendering with document.currentScriptSimon Willison · 2026-10-17
Inline rendering with document.currentScript Lean Rada describes a neat trick that takes advantage of the document.currentScript property. You can use that to drop in a tiny inline <script> element that replaces itself when the page loads: The year is <script> document.currentSc
web-edit 0.1a2Simon Willison · 2026-10-17
Release: web-edit 0.1a2 web-edit ( previously ) is my tiny web app for browsing and editing files in a folder. I mainly built it for editing files on different machines via Tailscale. I added a "copy to clipboard" option for both text and image data. I needed this because I was r
b11719llama.cpp Releases · 2026-10-18
ggml-cuda: fattn do not check oob if k_VKQ_max = (k_VKQ_max - nbatch_fa) ( #30572 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/57114852 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED m
b11718llama.cpp Releases · 2026-10-18
Restore ESIMD kernels on FFN path ( #30239 ) Reenable ESIMD on the FFN path Signed-off-by: Todd Malsbary
[email protected] Extend ESIMD fusion on FFN path to include Q8_0 Signed-off-by: Todd Malsbary
[email protected] Remove comment explicitly referencing ESIMD in tes
b11717llama.cpp Releases · 2026-10-18
hexagon: add support for hadamard MUL_MAT and GET_ROW for flat and tiled Q1_0 and Q2_0 ( #30627 ) hex-hadamard: add support for hadamard ops hex-mm: reduce pkt counts in the q8_1 quantizer and vec_dot_q1 hex-q1/q2: add support for flat and tiled GET_ROWS for Q1_0 and Q2_0 Co-auth
v0.40.7Ollama Releases · 2026-10-18
What's Changed openai: allow Responses effort on non-thinking models by @hoyyeva in #19010 llama-server: let llama-server infer the draft speculative type by @dhiltgen in #19064 mlx: add PPLX Decider v1.2 support by @dhiltgen in #19072 Full Changelog : v0.40.6...v0.40.7-rc0