ggml Ships 1.0.0

After years of rapid iteration under opaque build numbers, ggml — the tensor library at the core of llama.cpp, whisper.cpp, and stable-diffusion.cpp — shipped its first 1.0.0 release on November 13. The milestone removes deprecated APIs, bumps the RPC protocol to v9, and delivers broad backend improvements spanning CUDA FP8, Metal MoE fusion, Vulkan FlashAttention, and new kernels for Hexagon, OpenCL, and WebGPU.

Read more →

LLM 0.37 and the AI-Reviewed AI PR

Simon Willison's LLM CLI hit 0.37 on November 2, adding gpt-6.1 models, a simpler OpenAI-compatible endpoint setup command, and multimodal embeddings. The more interesting note is that nearly all 12 contributing authors used AI assistance, and Willison uses Opus 5.5 or GPT-6 Astra to triage those submissions — a small but clear snapshot of where open source maintenance is now.

Read more →

What You Know When the Internet's Gone

Survival LLM is a free, open-source offline AI assistant bundled with roughly 930,000 Wikipedia articles, medical references, FEMA guidance, and U.S. military survival manuals. It selects a model tier based on your machine's RAM and runs fully locally after the initial download. The interesting design question isn't the AI — it's what you bundle with it.

Read more →

Klein, Smaller, Better

Black Forest Labs released open weights for FLUX 3 Image Klein — a 5.6B parameter model that claims to outperform the larger FLUX.2 [pro] in text-to-image and editing tasks, while running on consumer GPUs with 8GB VRAM. 91 Elo points above FLUX.2 [klein] 9B with 38% fewer parameters.

Read more →

Bus Traffic as Source Material

Christian Schaller used Claude Code and a USB traffic capture harness to write a SANE backend for a Plustek film scanner, a Rust app for scanning negatives, and kernel plus libcamera fixes for a ThinkPad MIPI camera — a concrete account of AI taking over the tedious comparison work in hardware reverse engineering.

Read more →

OpenCode Grows a Nervous System

OpenCode 2.0 ships a rebuilt architecture: a single shared background server that connects the TUI, web interface, and desktop app; Code Mode — a native JS interpreter that lets the agent chain MCP tool calls as scripts rather than one-by-one; and a hot-reloadable plugin system stable enough that the agent can write plugins for itself mid-session.

Read more →

Codex Grew a Daemon

OpenAI's Codex CLI version 0.157.0 quietly started launching a persistent background process that self-updates hourly, runs from a copy of itself in ~/.codex/packages/, and doesn't stop when you close Codex or even run `daemon stop`. The HN thread surfaced it; the question it raises is whether AI coding tools are quietly becoming apps.

Read more →

The Agent That Rewrote Itself

Prime Intellect rewrote Prime Agent — their open-source coding agent harness, 300k downloads, 8 trillion tokens — from TypeScript to Rust using ~2,000 AI agents across 10,000+ sandboxes. The result is 13x faster startup, 5.7x less memory, and a nine-crate architecture with session isolation. A practical test of whether agent fleets can handle serious infrastructure work, not just toy tasks.

Read more →

Laying Out an Image Like a Document

Black Forest Labs ships FLUX 3 Image with bounding-box composition, multi-step targeted editing, and native 4K output — bringing structured spatial control to diffusion that was previously only available through ControlNet-style workarounds. Open weights announced for coming weeks.

Read more →

A Second Pair of Eyes on Your Agent

Claude Code 2.1.288 ships a built-in mod called "You should know" — a side agent that watches your main session and speaks up when it notices something you or Claude might miss. It's opt-in, requires telemetry, and represents a specific bet on how to surface the class of problems that slip through when you're not watching the terminal.

Read more →

Claude Code Grows a Mod System

Claude Code 2.1.287 ships mods: in-process TypeScript modules that can intercept, rewrite, and answer agent events before they reach the model. Unlike shell-script hooks, mods run inside the session, keep persistent state, and carry a rich sandbox API covering UI, tool routing, secret redaction, and custom slash commands. OpenAI Codex has had lifecycle hooks for a while — the two approaches reveal different theories about where agent customization should live.

Read more →

DSPy Comes to OTP

Imp 0.5.0 ports DSPy to Elixir and the BEAM runtime, bringing typed LLM signatures, multiple prompt optimizers, and agent loops backed by OTP supervision. It's early and experimental, but the combination of DSPy's systematic optimization approach and the actor model's fault tolerance is a genuinely interesting fit for production agentic systems.

Read more →

Jev on Your Own Metal

Ollaya ships as a Rust daemon that pulls open decision models (Laya, Decider, NLI, GLiClass, Von, Qwen3guard) locally and serves them behind a TypeSafe-compatible API. Set an environment variable and existing Jev clients point at localhost — 8–10 ms per five-question request on a 4090, no API key, Apache-2.0.

Read more →

The Agent Lives in a Lisp Image

Lambda Symbolics' Autolith is a Common Lisp programming agent that runs inside a live SBCL image it can inspect and redefine at runtime — a design that takes the Lisp machine idea of a persistent, self-modifiable environment and applies it to AI coding agents.

Read more →

The Unix-Friendly LLM CLI Grows Up

LLM 0.32, Simon Willison's CLI tool for talking to hundreds of models, ships its most significant update since launch: reasoning traces go to stderr, server-side tools replace local execution, and conversation logs adopt a Git-style content-addressable format. Three changes that each solve a real design problem cleanly.

Read more →