Sovereign Grid's avatar
Sovereign Grid
blog@sovgrid.org
npub1ymra...nzhn
Engineering log of a self-hosted AI build on NVIDIA DGX Spark, run from a flat in Europe. Open weights, open source, no KYC. Fix postmortems, model choices, distribution honesty at sovgrid.org.
Sovereign Grid's avatar
sovgrid 2 months ago
Sovereignty stopped being a thought experiment this week. The US ordered Anthropic to suspend access to its strongest models for every foreign national, inside or outside the United States, its own staff included. You either own your learning loop or you rent it until the day the lease ends. New post on what that actually costs at hobbyist scale:
Sovereign AI Blog
The Week the Dependency Changed Its Mind | Sovereign AI Blog
On June 13 2026 the US ordered Anthropic to cut off its strongest models for every foreign national on earth. The next day Microsoft
Sovereign Grid's avatar
sovgrid 2 months ago
The primary challenge is identity separation at every layer when the operator is a friend with zero Linux experience. Default-local privacy and a vibe-sustaining onboarding pattern are required to survive day three.
Sovereign AI Blog
Sovereign Friend-Setup: When You Build A Sovereign-AI Box For Someone Else | Sovereign AI Blog
Most sovereign-AI guides assume the operator is the same person as the user. What changes when the operator is your friend who has zero Linux exper...
 #SovereignAI #Lenovo
Sovereign Grid's avatar
sovgrid 2 months ago
A May 2026 memo stated local 8B models cannot reliably perform MCP tool-use. Late May retesting confirmed the models work but the bridge layer was broken. The original diagnosis regarding the cause was incorrect.
Sovereign AI Blog
We Were Wrong About Local 8B Tool-Use (2026 Reality Check) | Sovereign AI Blog
A May 2026 memo of mine said local 8B models cannot reliably do MCP tool-use. I retested in late May. The memo was specifically wrong about WHY. Di...
 #SovereignAI #Lenovo
Sovereign Grid's avatar
sovgrid 2 months ago
Qwen3.6 and Mistral Small 4 both passed the Python quality gate for the Start Here article despite fabricating hardware and benchmarks. The raw outputs required no editing before the scorer accepted them.
Sovereign AI Blog
The Quality Gate That Rewards Fabrication: I Had Qwen and Mistral Write This Blog | Sovereign AI Blog
This blog gates every article behind one Python scorer before it publishes. I gave Qwen3.6 and Mistral Small 4 the same brief, the Start Here hub a...
 #SovereignAI #DGXSpark
Sovereign Grid's avatar
sovgrid 3 months ago
Two new pieces, same method, one lesson. When a measurement returns an impossible result, suspect the instrument. 1. The 0/30 coding score that was a broken test harness:
Sovereign AI Blog
Mistral vs Qwen3.6 on DGX Spark: the 0/30 That Was a Broken Ruler | Sovereign AI Blog
I almost published
 2. The publication quality check that passed two AI-fabricated drafts:
Sovereign AI Blog
The Quality Gate That Rewards Fabrication: I Had Qwen and Mistral Write This Blog | Sovereign AI Blog
This blog gates every article behind one Python scorer before it publishes. I gave Qwen3.6 and Mistral Small 4 the same brief, the Start Here hub a...
↑