Subscribe
Sign in
Home
Podcast
Notes
ai-development
MCP Server
Archive
About
Latest
Top
Anthropic Shipped an AI Security Scanner. Here's the Per-PR Cost Math.
Before you add anything to CI, know exactly what it costs per pull request and how to triage what it finds.
Jun 2
•
James Cruce
Stop Paying for Cloud APIs: Building a Local AI Stack on Mac Studio
How to leverage Apple Silicon's unified memory for production-grade LLMs and replace your cloud billing entirely.
Jun 1
•
James Cruce
May 2026
The Pope Wrote a Memo to AI Developers. Most of You Missed It.
A builder's read of Magnifica Humanitas—what 'disarm AI' actually means, why 'alignment' alone isn't enough, and what to do about it in your config.
May 29
•
James Cruce
I Built a Self-Improving AI Swarm. After 100 Runs It Was No Better Than Run One.
What a flat leaderboard taught me about feedback loops, reward hacking, and why your judge matters more than your model.
May 25
•
James Cruce
Managing Anthropic Agent SDK Costs: A Post-June 15 Billing Playbook
Anthropic moves Agent SDK calls into a $100/mo credit pool on June 15. Here's the two-phase mitigation I shipped: a billing cap plus a provider router.
May 16
•
James Cruce
ChatGPT Just Invented an Entirely Fake Version of My MCP Server
When AI engines don't have you indexed, they don't say 'I don't know.' They confidently make something up. Here's the receipt, and the weekly test I…
May 8
•
James Cruce
1
The Ollama Model-Swap Death Spiral That Killed Every Cron at Once
One Mac Studio, multiple crons, fallback chains. Here's how Ollama model swaps cascade into total failure, and the two-line fix that stopped it cold.
May 6
•
James Cruce
1
I Killed OpenClaw and Built ClaudeClaw Mission Control
Retiring OpenClaw, migrating to ClaudeClaw Mission Control, and what five days of teardown taught me about operational blindness.
May 2
•
James Cruce
1
1
April 2026
Nightshift: I Went to Sleep and My Mac Ran 118 Experiments
What I learned about disciplined iteration from Karpathy's autoresearch loop running overnight on an M3 Ultra.
Apr 22
•
James Cruce
Hosted RAG vs. Self-Hosted RAG for MCP Servers—When Does Paying Actually Win?
A practical comparison of Cloudflare AI Search, Bedrock Knowledge Bases, Pinecone Assistants, LlamaCloud, and self-hosted sqlite-vec for powering MCP…
Apr 21
•
James Cruce
What's the Future of MCP Servers in 2026-2027?
MCP servers have gone from a niche protocol announcement to the backbone of AI tool integration in under two years.
Apr 13
•
James Cruce
1
How Do I Automate Workflows with AI Agents?
Agent workflows combine AI reasoning with tool access and scheduling to complete multi-step tasks autonomously. The architecture ranges from simple (one…
Apr 13
•
James Cruce
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts