Fetching from the wire…
01
02
03
04
05
06
07
08
Infra2026-09-19 · source-backed
incoai/splash launched September 18 under Apache 2.0, reporting 2x decode speed on Qwen3.8-27B on a 48GB M5 Pro and 282ms to first token with a 32K context cached. The argument is anti-generality: kernels, draft model and memory plan are specialized per served model, which is why there's nothing to configure. It speaks OpenAI Chat Completions, OpenAI Responses and Anthropic Messages with streaming, tool calls, JSON Schema output, images and inline PDFs. GitHub Requires M3 or newer, macOS 26.4, 36GB unified memory.
Each link below shares sources, entities, or timing with this story.
Three moves, two days, no coordination between them. August 10–11: GitHub shipped Ollama as a BYOK provider inside Copilot for JetBrains (GitHub Changelog). Unsloth released Unsloth Desktop with a command literally named unsloth start claude, which points Claude Code and Codex...
You noticed the Mac mini shortage. Here's what caused it. The Information reported, via Cult of Mac, that OpenAI has purchased tens of thousands of M5 Pro and M6 Mac minis plus M5 Max and Ultra Mac Studios over the past several months, running reinforcement learning and comput...
Lily is Apache 2.0 inside pplx-garden, a small Metal inference server built for Qwen3.6-35B-A3B converted to MLX affine 4-bit, exposing a minimal OpenAI-compatible chat API with greedy decoding. The README explicitly rules out dense and smaller Qwen checkpoints, BF16, GGUF, AW...
For about a year, "run your agent locally" meant accepting a model that couldn't reliably call a tool twice in a row. That excuse is gone. Meta Superintelligence Labs published Muse Glimmer today: a 29.6B dense causal transformer, 52 layers, 6,656 hidden dim, with a ~1.8B ViT-...
Anthropic released Claude Fable 5.1 on September 1. Claude Code v2.1.257 made it the default Fable model at 17:53 UTC that day, with a 1M-token context window, $10 per million input tokens, $50 per million output, and $0.25 per million on cache reads (claude-code CHANGELOG). B...
Marcel Pociot's experimental app, published September 14 at 173 stars two days later, routes system-level Siri and Shortcuts requests to a local Claude Code session with its tools and file access instead of to Apple's own model. Small repo, but the first concrete example of Ap...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.