ambient-code.ai

Think about how much will change in the AI landscape during the lifetime of your next application. You can bet on improvements to code generation models, hardware, talent, review capabilities and more. This leads us to the need for a new metrics: something like TCO, but that also represents efficiency. I propose Value Per Token… — read more

In the near future, it’s entirely plausible that your entire codebase will be written, refactored, and evolved by AI agents. But the “brownfield” you’ll inherit won’t be legacy human code, it will be legacy AI decisions. And those decisions will stem from choices you make today. For example, whether and when to adopt an AI-first… — read more

The shift to Ambient Code isn’t about replacing developers. It’s about evolving what development means. There are valid concerns AND solvable problems. Leaving engineering efficiency on the table is not an option. “I Don’t Trust AI-Generated Code” Ambient Code works the same way. You don’t trust the code because an AI wrote it. You trust… — read more

Hey folks, I’ve been spending a lot of time thinking about how we write software. Actually, this was spurred on by a recent project: I thought, how can I drive inference workloads to llm-d? How can I keep vLLM “hot”? codegen is an inference-heavy workload, so let me look deeper. What I found was a… — read more