Topic

AI

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.

NVFP4 does not range from -8 to 7.5: the 16 values, correctedNote
Research

NVFP4 does not range from -8 to 7.5: the 16 values, corrected

The NVFP4 range is not -8 to 7.5. Its 16 bit patterns hold just 15 values, from -6 to 6,…

7 min
The largest distillation attack yet: the Alibaba numbersAI security
Research

The largest distillation attack yet: the Alibaba numbers

Somewhere between late April and early June, a machine somewhere opened a fresh conversation with Claude roughly every seventh of…

5 min
Bonsai 27B vs Gemma 4 31B on a Mac: which local model to run1-bit LLM
Guides

Bonsai 27B vs Gemma 4 31B on a Mac: which local model to run

Two models sat loaded in the same copy of LM Studio this week, and one of them was a fifth…

6 min
Bonsai 27B 1-bit on a Mac: a 27B model in 3.8 GB1-bit LLM
Guides

Bonsai 27B 1-bit on a Mac: a 27B model in 3.8 GB

Most 27-billion-parameter models arrive as a download you plan an evening around. The Bonsai 27B 1-bit build from PrismML lands…

8 min
Does your AI phone home? The StrideNote telemetry investigationsTelemetry
Research

Does your AI phone home? The StrideNote telemetry investigations

Does your AI phone home? Our telemetry investigations tested seven local AI tools, captured what each one sent, and show…

7 min
AI for beginners: a new hands-on course from StrideNotePress release
News

AI for beginners: a new hands-on course from StrideNote

AI for beginners, done the StrideNote way: a new hands-on course on StrideNote Education that teaches the basics with no…

2 min
AI privacy and data control: where StrideNote standsPress release
News

AI privacy and data control: where StrideNote stands

AI privacy and data control start with proof, not promises. Here is where StrideNote stands: verify what a tool sends,…

2 min
How AI companies hide tracking code, from Claude Code to your local toolsNote
Research

How AI companies hide tracking code, from Claude Code to your local tools

AI tracking code hides in plain sight. We break down the covert tracker Anthropic shipped in Claude Code, the telemetry…

6 min
How to keep a background AI agent from failing silentlyautomation
Guides

How to keep a background AI agent from failing silently

A background AI agent silent failure hides in plain sight. A heartbeat, a cron wrapper, and a watchdog make a…

6 min
Graphify has 81,000 stars. We read the code instead of running itgraphify
Research

Graphify has 81,000 stars. We read the code instead of running it

Graphify has 81,000 GitHub stars in three months. We read the Graphify source instead of running it: zero telemetry, local-first…

8 min