I don't want to cause panic, but I'm paranoid
Attacks and vulnerability discovery are being automated. What I saw on pwn.watch, what I changed in my own setup, and why critical infrastructure keeps me up.
Published · Nov 6
Blog
Notes from production systems, edge hardware, and AI reliability. First on the site, later on YouTube.
Two posts published, three in progress. Each one comes from something I actually shipped or dug into, with the parts that broke included.
Attacks and vulnerability discovery are being automated. What I saw on pwn.watch, what I changed in my own setup, and why critical infrastructure keeps me up.
Published · Nov 6
The 80% DeepSWE score everyone shared was a 10-task subset. The full 113-task run says 58.4%. Tokenizer forensics, real adoption numbers, and why your work code should stay away from it.
Published · Aug 23
What actually broke connecting a Raspberry Pi to AWS in under seven days, and what I would do differently.
Device provisioning and certificates, connectivity that drops in the field, and the telemetry pipeline that had to survive all of it. The checklist I wish I had on day one.
Pipeline
How an employment AI pipeline looks when you do not blindly trust model output: explainability, guardrails, and fallbacks.
From the matching work at Mi Primera Chamba: why every score needs a reason, how prompt injection defenses hold up against real CVs, and what happens when the model is simply wrong.
Coming soon
How to add CI and testing to a fast-moving team, without slowing down the shipping.
Testing by cost of failure, the first three tests worth writing, and how to make CI something the team asks for instead of something it tolerates.
Coming soon
Questions about any of these topics, or a post you want to see first? Email is fastest and I answer every one.