Insights
No model card states the compute threshold
The EU AI Act draws its line at 10^25 operations, California and New York at 10^26. Three open-weights cards, none says.
7 minAI
Everything we publish on AI: the models we run on our own machines, what the tools send home, the benchmarks we measure ourselves and the claims we check against the code. Start with the investigations, then the guides.
Investigations
ArtCraft phones home before you sign in
Google Tag Manager and Microsoft Clarity load first. The source has no switch to turn them off.
7 min
Investigations
Claude Code on a local model mostly describes its tools
Pointed at local hardware it works; 74 percent of the 29,424 tokens it sends before starting are tool definitions.
7 min
Reports
Sixteen coding agents, and what each one sends home
The Local Agent Telemetry Report 2026 tests them on one Mac: who hears from each, and the settings that make it quiet. Free PDF.
11 min
Reports
Seven local AI tools, and which ones phone home
The Local AI Telemetry Report 2026 tests them on one Mac: what they send and which off switches work. Free PDF and dataset.
15 min
Guides
Kokoro narrates an article in a seventh of its length
Install Kokoro TTS on a Mac with no ffmpeg, a measured 7.1x real time on an M4 Pro, and a job that narrates new pieces on its own.
6 min
Guides
One skills folder can serve four coding agents
Where Claude Code, OpenCode, Hermes Agent and Pi each look, and the 106 dead paths that broke ours.
7 min
Insights
Skills add knowledge, MCP adds hands
A skill is files on disk; an MCP server is tools over a protocol. The specs, the context cost, and the servers we run.
8 min
Insights
Speculative decoding and MTP are one trick in two places
A separate draft model or draft layers inside the model. The llama.cpp flags and the acceptance rates we measured on two Qwen models.
17 min
News
OpenClaw agents can read each other’s sessions by default
Version 2026.9.2 opens sessions across a shared Gateway. The change was reviewed as a security boundary before it merged.
6 min