AI cost per task: why AI feels pricier as it gets cheaper
Frontier AI runs cost more every year, but at fixed quality AI cost per task is falling about 13x a year. Why both are true, and the rate I'd plan agents on.
Tag · 28 essays
Frontier AI runs cost more every year, but at fixed quality AI cost per task is falling about 13x a year. Why both are true, and the rate I'd plan agents on.
Here's my current AI stack: open source, a dedicated memory system, multi-agent access, spec judges, evals, and as much of the process in code as possible.
A git-owned knowledge base is markdown in a repo you control. A YC launch listed that as a hack. You want a record you can diff, refuse, and take with you.
The piece I wrote on harnesses described five component layers that every production agentic system needs: orchestration and planning, an execution environment, validation and quality control, context and memory management, and logic and interaction.
Shop CLI: A Tool Built for AI Agents, Not Humans
Not all business relationships do the same job. Research shows which ones survive the agentic economy, and which were always just expensive due diligence.
The skill that actually makes AI useful: meta-prompting
Fable is back. And it's changing how I think about thinking.
Antony Evans argues that building an AI system is farming, not hunting: there is no finished, shipped state, only a system you keep tending as models change.
Google launched AI checkout at scale. Your store is in the system. You still won't appear. Here's the part nobody is explaining.
I set out to build a DTC store almost entirely with AI.
Not all business relationships do the same job. Research shows which ones survive the agentic economy, and which were always just expensive due diligence.