Renovate or Rebuild? Why I Redid the Blog From Scratch
My blog ran on someone else’s theme for five years. I finally stopped patching and rebuilt from the studs. Zero dependencies, LLMO-ready, accessibility-first, and the bee was the answer all …
Writing
Posts
Subscribe via RSS →How Much Does It Cost to Self-Host Open Models on AWS?
Your AI bill tripled last quarter and your CTO is asking about open models. Here’s the real hardware, real costs, and whether it makes sense for a team of 10 or a company of 500.
Tomorrow Is Coming to Collect
The top 1% of companies spend $7,500/employee/month on AI. Token prices dropped 98% but bills tripled. 84% of CFOs see no ROI. The AI spending binge is over and the bill is arriving.
The OWASP Agentic AI Top 10: What Builders on AWS Need to Know
This is post #0 of the OWASP Agentic AI Top 10: What Builders on AWS Need to Know series. You’ve secured your GenAI chatbot. You’ve got prompt injection filters, output validation, maybe …
Agent Goal Hijack: When Your AI Agent Works for Someone Else (ASI01)
This is post #1 of the OWASP Agentic AI Top 10: What Builders on AWS Need to Know series. You build an agent. You give it a clear goal: “Help customers check their order status.” You test …
Tool Misuse & Exploitation: When Your Agent's Legitimate Tools Become Weapons (ASI02)
This is post #2 of the OWASP Agentic AI Top 10: What Builders on AWS Need to Know series. Your customer service agent has access to an email tool. Makes sense. It needs to send order confirmations. …
Identity & Privilege Abuse: When Your Agent Acts Like It Owns the Place (ASI03)
This is post #3 of the OWASP Agentic AI Top 10: What Builders on AWS Need to Know series. Your engineering manager builds an agent to help her team. She gives it access to the team’s Jira board, …
Agentic Supply Chain Vulnerabilities: Your Agent Is Only as Secure as Its Weakest Plugin (ASI04)
This is post #4 of the OWASP Agentic AI Top 10: What Builders on AWS Need to Know series. You install an MCP server from npm. It says “postmark-mcp” on the label. Looks legitimate. Has a …
Unexpected Code Execution: When Your Agent Becomes a Shell (ASI05)
This is post #5 of the OWASP Agentic AI Top 10: What Builders on AWS Need to Know series. I wrote about the trust gap with coding assistants in Your Coding Assistant Is Not You. But when agents can …
Memory & Context Poisoning: When Your Agent's Memory Becomes a Weapon (ASI06)
This is post #6 of the OWASP Agentic AI Top 10: What Builders on AWS Need to Know series. Your agent has been working perfectly for weeks. It answers customer questions accurately, retrieves the right …