I build AI agent systems from scratch and write about what breaks along the way.
Recent
-
Designing tools that AI can actually use
The tool description is a big part of the interface. If the model can't tell when to call a tool from its description and schema, quality falls apart.
-
Loading code without the disk: what each OS lets you get away with
memfd, PE loaders, unlink-after-dlopen. Three operating systems, three different definitions of 'in memory'.
-
paker: load encrypted Python packages from memory
Encrypt a Python package tree, ship it over the network, load it from memory. What works, what doesn't.