Daily digest for 2026-10-29 · 13 new stories (previously covered stories are never reposted)
Quoting Ted SandersSimon Willison · 2026-10-28
In general, LLM performance is incredibly multidimensional. There's no guarantee of a fixed ordering where the model that is best at math is also the model that's best at jokes. Despite that complexity, much of the variation in performance is explained by just a single variable:
GitHub Octoverse 2026Simon Willison · 2026-10-28
GitHub Octoverse 2026 I'm at GitHub Universe today (GitHub gave me a free ticket through their "GitHub Stars" program). EVP Jay Parikh just announced this year's Octoverse report, and highlighted these numbers in particular: This is a pretty stark representation of the impact of
The October inflection point for vibe game developmentSimon Willison · 2026-10-28
I've written before about how November 2025 was an inflection point for coding agents - the point where Opus 4.5 and GPT-5.1 crossed a tipping point that meant their respective coding agents became reliable daily drivers for software engineers. I think we've reached a new inflect
v0.8.0llama.cpp Releases · 2026-10-28
Overview This release adds the LiquidAI LFM3 family (text, vision, audio and omni) together with a new experimental streaming-audio API in mtmd , and wires realtime audio in and out of the server through the new /v1/realtime and /tts endpoints. A batch of new architectures landed
b11982llama.cpp Releases · 2026-10-29
hexagon: support for UPSCALE op ( #31331 ) hex-upscale: basic upscale ops (not fully vectorized) hex-upscale: optimize nearest 2x, 4x and bilinear 4x hex-upscale: add support for non-contig rows and dims collapsing hex-upscale: use vgather instead of scalar staging hex-upscale: m
b11981llama.cpp Releases · 2026-10-29
hexagon: improve DDR bw utilization in transposed CONCAT ( #31277 ) hex-concat: double row block size for transposed CONCAT hex-concat: double buffer scratchpads hex-concat: chunked src1 rows in transposed concat hex-concat: pad src1 VTCM stride to spread gather lanes hex-vgather
v0.40.13Ollama Releases · 2026-10-29
LFM3 on Linux and Windows Liquid AI's LFM3 models, including text-to-speech in lfm3-audio and lfm3-omni , now run on Linux and Windows as well as Apple silicon. Full Changelog : v0.40.12...v0.40.13
v0.40.13-rc1: llama.cpp: workaround Metal unary crash (#19372)Ollama Releases · 2026-10-28
This temporary patch works around a regression on older versions of MacOS ggml_metal_library_compile_all: failed to build 'unary' library
v0.40.13-rc0Ollama Releases · 2026-10-28
llama.cpp: version bump b11963 ( #19360 )