Identity · Security · AI infrastructure
I write down the things I learn, usually after I've made the mistake first. Long-form posts on what I'm building, breaking, and defending.
A viral post said 90% of Anthropic engineers moved to agentic graphs and stopped prompting. The number has no source and the video was a Claude Code demo. The architecture underneath is still worth learning.
Running Wan 2.2 image-to-video on a DGX Spark to make a hidden scene breathe: the undocumented Blackwell setup traps and the trick behind it.
Claude Fable 5 is the most capable model Anthropic has shipped. It also blocks legit security work and drops the zero-retention floor businesses chose it for.
A pocket travel router with an IPsec tunnel back to a network I control, broadcasting a trusted SSID that follows me into every hotel and airport.
Claude Opus 4.8 is a sharpening, not a leap. Clear gains, more honesty, hundreds of parallel subagents, and what it all means for security teams.
A hands-on first-hours review of Claude Opus 4.7. What moved, what broke, the token-cost gotchas, and why Anthropic is still holding Mythos back.
A sharp take on why today’s AI agents feel wrong, and what a quieter, more persistent AI-native future could actually look like.
