Blog Archive

The token gap

Last October, ten billion lifetime tokens earned developers a public tribute at OpenAI DevDay. This June, one Umans AI user ran nearly eleven billion tokens in a single day. What that says about token demand, compute supply, and the serving efficiency that has to close the gap between them.

Tokenomics, behind the scenes

Put the exact same model on GPUs and its token production cost can vary by multiples depending on how you serve it. A walk through the economics of a token: the frontier, the dollars it turns into, the levers that move it, and the claim our measurements let us make.

DeepSeek V4 Pro DSpark: the model isn't ready, the architecture is

We served DeepSeek V4 Pro for two days. What we wanted was hands on the architecture: attention that scales almost linearly instead of quadratically, and a speculative decoder that adapts to load. Both delivered. The preview checkpoint did not.

GLM-5.2 NVFP4: fast, cheap, and not worth serving

We put an NVFP4 build of GLM-5.2 in front of real users for four days, at 200+ tokens per second. Users called it intoxicating. We retired it anyway: if the tokens are not useful, they are not worth serving, no matter how efficiently we can produce them.

How We Actually Ship with AI

The concrete workflow we use to go from a vague idea to code running in production, with AI agents doing the heavy lifting. Three moves, one increment file, everything in git.

Stop Being Your AI Agent's Assistant

When we launched code.umans.ai at the beginning of February, my cofounder Naji and I saw it as an opportunity to challenge ourselves. We had unlimited LLM access now. No more token anxiety. So we asked: what happens if we really let our agents work autonomously?

GLM-5 vs Kimi-K2.5: Long-context serving at scale

Why GLM-5 is a real step forward compared to GLM-4.7 for serving long-context coding agents, and why we still keep Kimi-K2.5 as the default for the best experience.

Shipping Solo With AI Agents Without Reading the Code

A new abstraction is emerging for solo building: iterate on intent with an AI agent, run, refine, and read little code. What enables it now, and where it breaks.