Hi, I'm Patrick — you might know me as @trashpandaemoji on X. I've worked across the web stack, managed teams, and these days I'm a senior SWE at a large tech company working on a gen AI enabled feature. Most of what I think about is model training, evaluations, agents, NLP, and what it takes to build products with generative AI.
This is where I write about it, with some help. A post usually starts as my own notes, an outline, or a voice transcript. I pass that along to a few different models and let each one write its own version, then publish whichever I like best — sometimes that's a model's, sometimes it's mine. The versions I didn't pick stay on the page, so you can switch between them and see how the same piece sounds in a different voice.
The latest is just below, and everything else lives under Posts.
The relay economy is a large, commoditized grey market: hundreds of storefronts on a handful of open-source gateways. Some of what it sells is legitimate resale, but much rests on two fragile foundations.
Patrick wanted a fast, live voice chat with his agents. What shipped is slower and simpler: any thread can listen and read its replies aloud, and the voice it uses is a setting he can swap.
Patrick handed his agents' traffic calls to Jev, a fast judgment model. It was much faster than asking an agent, but too cautious, so he retuned it to interrupt.
Astra made a 3D Bufo and a run of short animations Patrick loved. The full music video was too much.
The pet's tools worked, but Patrick's agents mostly ignored it. He deleted the plugin that afternoon.
A phone scan gave Codex the house's shape, but Patrick still had to design the rooms himself.
A local cache for everything Patrick saw became an event stream, but never found a clear job.
Patrick tried flow outlines, agent explainers, and a concept language, but still lacks a map he can use to explore unfamiliar code.
From Council to Bot Teams: a shared room for specialist agents, with the hard work of making their updates useful still underway.
Fucc Boi Bench became a refusal test. BufoBench showed why judging a handmade frog still takes a human eye.
Four attempts to make agent work easier to follow, and why Patrick now builds on bb.