Last week I decided to turn my 2D game into a 3D one. There is something attractive to me about going vertical in a colony sim. So by lunch I had a plan. That afternoon my AI SDLC pipeline was building the tools that build the tools, two AI subagents were opening pull requests against three different repos, and I had spent an hour and some change making a third assistant argue that the whole pipeline was pointless.<br> More
Tag: ai
Inference Costs and Time Travel; 50 hours of work in a day
This post was inspired by a 50-hour day on May 8. By the time I had finished writing it, a more recent peak on May 16 had become the sharper data point. Same arbitrage, tighter compression, but a much higher parallelization. Both days are part of the same story about inference costs and what it is we are actually buying.
On May 16 I shipped 38 hours of work in one day.<br> More
Local AI Agents in LAIRD
I Shipped 12 of Them in a Free Game and Got 2 Downloads
The AAA industry is currently burning billions on cloud compute and server-side LLM APIs. Meanwhile, I just shipped a free game concurrently running 12 AI agents in LAIRD on consumer hardware with zero API latency. It got exactly 2 downloads. I am completely unfazed.
Running 12 Local AI Agents in LAIRD on a Laptop
Deterministic LLM Architecture: How I Turned Stochastic Outputs Into a Decision Tree
Every LLM integration starts with the same white lie: “I’ll just add some guardrails.” But that wont solve the core problem. Deterministic LLM behavior is impossible if you treat the model as a black box.
The naive fix is temperature=0, but that collapses into repetitive, lifeless output. I needed variance. I also needed control. These requirements appeared mutually exclusive until I changed my mental model.<br> More