Most engineers think GC is slow. They’re wrong. Coordination is slow. Pony’s per-actor heaps and message-passing model eliminate the coordination that makes traditional garbage collectors a performance problem.

An attention focus tells an agent where to look. A persona tells it how to think.

Marco Primi and I join David Wynn on Bug Bash to talk about workloads — what they are, why they matter for testing distributed systems, and how even a simple while true loop can expose bugs your unit tests miss.

Small differences in prompts produce wildly different outputs. You can fight that or you can use it.

I treated Claude like a junior engineer, taught it principles, and watched it grow. Two weeks later, it’s on my short list.

The ideas behind Parma, explained like we’re sitting at a bar and you asked me what I’d been working on.

How Peter Alvaro’s lineage-driven fault injection clicked with me, and why I ended up at Antithesis.

Sylvan Clebsch, Mike Shah, and I talk about how Pony came to be, walk through Pony Patterns, and discuss the language’s design.

Kris Jenkins and I dig into reference capabilities, Pony’s actor model, and how it implements garbage collection without stop-the-world pauses.

Parma adds less than one percent overhead beyond the underlying TEE while ensuring a security invariant over all reachable states of the container group.