AI News Update

Daily digest for 2026-11-18 · 13 new stories (previously covered stories are never reposted)

Hugging Face Trending4

harness-hub/Qwen3.8-27B-pi-adapted
Hugging Face Trending
chatrlabs/Qwen-Image-2.1-Uncensored-Omni-Quantized
Hugging Face Trending
n4ze3m/tiny-voca
Hugging Face Trending
meituan-longcat/LongCat-Video-Avatar-1.6
Hugging Face Trending

Simon Willison3

External sandboxes for coding agents
Simon Willison · 2026-11-17
External sandboxes for coding agents I've been exploring new ways to sandbox code that is executed by agents, with a focus on making it safer to try out local models without worrying that a mistake or prompt injection attack might cause them to take damaging actions on a machine.
GPT‑6.2 Astra and GPT‑6.2 Sol
Simon Willison · 2026-11-17
GPT‑6.2 Astra and GPT‑6.2 Sol OpenAI: We’re introducing GPT‑6.2 Astra, our new frontier model for your hardest projects, and GPT‑6.2 Sol, our efficient, versatile model for everyday work. They're available in the API as gpt-6.2-astra and gpt-6.2-sol . I shipped LLM 0.38 with supp
Running the full server-side Datasette Python app in the browser with service workers and Pyodide
Simon Willison · 2026-11-17
Datasette Lite is my port of the Datasette Python application to run directly in the browser using WebAssembly and Pyodide . I've released a complete rewrite of Datasette Lite using service workers, and it's now almost indistinguishable from the real server-side application. You

llama.cpp Releases6

b12506: vulkan: add bfloat16 support to various ops (#32202)
llama.cpp Releases · 2026-11-18
vulkan: expand bf16 support for unary and binary ops and rms_norm cpu: add bf16 support for scale, clamp, leaky_relu, swiglu_oai, swiglu_clamp, tri and diag fix sycl fill supports_op condition restore CUDA op order
b12511
llama.cpp Releases · 2026-11-18
server: fix transcription prompt for v1/realtime ( #32507 )
b12504
llama.cpp Releases · 2026-11-18
cuda : increase Pascal DP4A MMQ I tile for J=64 ( #31352 )
b12509: unicode : add continuation check lambda (#31070)
llama.cpp Releases · 2026-11-18
This commit adds a lambda to check if a specified byte is not a valid continuation byte in a multibyte UTF8 sequence. The motivation for this is to improve readability and avoid some code duplication.
b12508: cuda : fuse NORM + MUL (+ ADD) (#32454)
llama.cpp Releases · 2026-11-18
Assisted-by: Codex
b12507: vocab : extract bpe_rank loading into function (#30962)
llama.cpp Releases · 2026-11-18
vocab : extract bpe_rank loading into function This commit extracts the BPE rank loading logic into a separate function named load_bpe_ranks . The motivation for this is that the came code is currently used by both gpt2/hybriddna/whitespace tokenizer models and gemma4 and this av