IDEAS, DECISIONS & LESSONS

Journal

Notes on AI, architecture and building useful products.

Explore AI Ideas & Solutions

1,005 articles

· 4 min read

ai-agents

Three LLMs, 621 Messages, 30 Hours: How AI Rooted a Fire Tablet

A researcher chained Kimi K3, GLM-5.2, and GLM-5.3 to build a working root exploit for an unpatched Fire OS kernel vulnerability. It's a genuinely useful case study in what long-horizon, multi-model agent security research looks like right now — and what it means for anyone running EOL hardware or unattended agents.

Read more

· 7 min read

agentic engineering

I Built a Self-Hosted Devin -- The Architecture of an Autonomous Engineer You Own

Devin costs $500/mo. Cursor's background agents live in someone else's cloud with your code. So I built the same capability on my own machines, on a Claude subscription I already pay for. Here is the full architecture -- the loop, the data model, the six-phase build, the hardening -- and why 70% of it was infrastructure I already had.

Read more