Poiesic Systems

In 1953, a twenty-seven-year-old man named Henry Molaison underwent surgery to treat severe epilepsy. Surgeons removed most of his hippocampus, a small curved structure deep in the temporal lobe, from both hemispheres. The seizures improved. Henry stopped making long-term memories.

Henry could carry on a perfectly coherent conversation. His intelligence was intact. His working memory functioned normally. He could hold information in mind, reason about it, and respond appropriately. He had full access to memories formed before the surgery. His personality was unchanged.

He just couldn’t form new long-term memories. Every conversation started fresh. His doctors reintroduced themselves at every visit for the next fifty-five years. He could read the same magazine and find it novel each time. He would grieve his uncle’s death anew every time someone told him.

There’s a new discipline coming to software engineering. I’m calling it forensic refactoring: the practice of reverse-engineering intent from code that never had any.

The last two years have been hard. The kind of hard that makes you want to demand to speak with life’s manager so you can punch them in the throat. I’m not going to catalog the specifics because this isn’t that kind of post and you’re not my therapist. But 2024 and 2025 tested me in ways I wasn’t prepared for. There were times where I wasn’t sure that I’d be equal to the challenge.

In the few hours a day I’m not spending on building Collabchek I’ve been hacking on a personal AI chat client. I’ve used several and the one that’s come closest to what I want has been sigogden’s very cool aichat project which I encourage you to check out. I’ve liberally borrowed several good ideas from their code.

As I’ve explored I’ve come to realize my requirements are somewhat unique.

Here’s a quick hack I came up with while experimenting with git worktrees and multiple coding agents and dealing with pod naming collisions when bringing up multiple copies of my local dev stack.