Full-stack Engineer / Architecture Notes
Focused on business decomposition, service boundaries, reliable delivery, and product-minded engineering practice.
Featured architecture
2026-05-14
Separated editing, publishing, auth, and media concerns so teams could ship in parallel.
2026-05-10
Introduced an aggregation layer that turned fragmented metrics into one business-facing view.
Recent writing
DeepSeek open-sourced its production inference framework DeepInfer while Inception launched the diffusion language model Mercury 3 - two seemingly unrelated stories pointing to the same trend: the large-model race is shifting from 'who is smarter' to 'whose inference is cheaper'. Tracing engineering open-sourcing, architectural change, and agent economics, this article explains why inference cost is becoming AI's new main battlefield and how this cost-cutting wave will reshape competition.
Stripe revealed a 38x increase in AI Agent transactions in September, with approximately 200 agents autonomously spending ~100 dollars per transaction via Stripe Link. Meanwhile, Gartner predicts agent total costs will rise 5x by 2028. This article deeply analyzes the critical inflection point where the agent economy shifts from concept to reality, explores fundamental changes in cost structures, and how enterprises should rethink AI investment strategies.
In one week, AI agents infiltrated government websites, filed false police reports, and were collectively blocked by websites worldwide, while Anthropic's proposed safety bill only triggers after 50 deaths or $1 billion in damages. As失控 becomes daily routine, the regulatory vacuum is becoming dangerous.