The open‑source llama.cpp library released version b11486 on Oct 8 2026, improving GELU activation accuracy and adding new binaries for macOS, iOS and Linux.
NoteBy OossaPublished by Oossa: 1 min read
The ggml‑org team published llama.cpp version b11486 on Oct 8 2026. The update improves the accuracy of the GELU activation function, a small math piece used in many language models. It also provides pre‑built binaries for Apple Silicon, Intel macOS, iOS, and several Ubuntu configurations (CPU, Vulkan, CUDA). The binaries can be downloaded directly from the release page.
Developers can run LLaMA models faster and with more precise calculations on their own machines.
Models
The company’s new three‑agent Claude‑based reviewer found 73.43% of core‑claim errors, far above the previous best of 14.81%.
Models
Mistral's new trillion‑parameter model scores 38 on an independent index, but costs more per task than competing open models.
Models
OpenAI reported two influence campaigns that used AI‑generated content to plant false stories in real media and blocked the involved accounts.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
