How Low Can Inference Go?
The modern software stack lives several layers above bare metal. How much of it exists only because humans were in the loop?
Ideas
Ideas that emerge from building products, written down once they have survived contact with production.
Essays
Time Is a Security Boundary
Automated attacks thrive on chaining small actions without interruption. Deliberate slow points break the chain: delay gives the rest of the system time to react.
The Flame
Every living thing on Earth is part of one unbroken chain nearly four billion years old. What if civilization's objective function were keeping that flame alive?
Bring Your Own AI
If the application owns the semantics, why does it also need to own the intelligence? Welcome agents as first-class users: the application becomes stable, the intelligence becomes portable.
Ludicrous Speed
How we build products at Commons now. Ideas become issues, agents turn them into merged, deployed software, and the default state is shipping.
A regeneration manifesto
Notes on building software that tries to last.
Building Anton
A series on building a personal agent OS from scratch, one chapter per real step: the wins, the dead ends, and the numbers.
Technical Notes
Gemma 4 NVFP4 on the DGX Spark: 271 tok/s at 8 concurrent, native tool calling and reasoning
Native tool calling and reasoning mode on Gemma 4 NVFP4 over 128GB of unified memory.
50+ tokens per second on a desktop: running LLMs on the NVIDIA DGX Spark
Standing up a 30B-parameter LLM at 50+ tok/s on the NVIDIA DGX Spark, the technical journey.