Vibe coding works for the first week or two. You describe what you want, the agent writes it, tests pass, you ship. A few weeks in, progress falls off a cliff. New prompts start breaking older features in ways that pass the obvious tests, but later surface in production. Vibe coding is the version where you fully trust the agent, don’t read or only skim the code, and ship. Agentic coding is the…
Three months on from the last status update , the Eignex rewrite has actually moved. The original plan was to split one tangled experimentation library into focused pieces, and that’s mostly what’s happened. Quick checkpoint on where things landed. How the stack converged The big shift since February is that kumulant and (soon) combo now share a single API shape for declaring computation graphs…
Imagine a D&D character sheet. It has typed fields (Strength 1 to 18, Class is Fighter or Wizard or Rogue) and rules between them (Halflings can’t be Paladins, Hit Points depend on Class and Constitution). The blank sheet is the schema ; a filled-in character is one instance of it. If you only have one schema, you can just write a CharacterSheet data class with the right fields plus some…
I keep seeing the same argument about AI making us dumber. It’s the same argument people had about search engines, and before that books. The usual response is to point at history and say “every generation panics, every generation was wrong, relax.” I think that response is half right, and the wrong half is what bothers me. Tools change what we bother to remember. The people who’d trained their…
Over the past few years, I found myself occasionally writing the same boilerplate: manually packing bits of application state into tight, heavily character-limited strings. It ended up with me creating a library for it called kencode. But first it’s story time… and then a little explanation of the underlying tech of why kotlinx.serialization is so cool and THEN I’ll go over kencode. It all started…
Time flies when you’re deep in code. I’m a bit behind on updates, but progress has been solid. Since the last post, I’ve wrapped up kencode and pushed further into kumulant . I haven’t really written up the bigger vision or architecture yet, so this is a first pass. The idea behind Eignex is simple. Take continuous optimization seriously in production systems. Instead of chasing local tweaks or…
I’ve always been fascinated by applying optimization to solve real-world problems. It is often an inherently multidisciplinary activity, and there is something deeply satisfying about taking distinct, often siloed ideas and jamming them together to create something that is fundamentally better than the sum of its parts. In my PhD thesis it was search-based optimization, multi-armed bandit…