I used to think building software was mostly about being precise. You write a function, you know exactly what it does, and if it breaks, you can trace the break back to a line of code. This is the world of classical AI—expert systems, decision trees, rule engines. It’s Newtonian. Give me the initial conditions, and I’ll tell you exactly where the apple lands. Then LLMs showed up, and the ground shifted. ...
There’s a particular kind of satisfaction in finding out that a “hard integration problem” was actually three small problems stacked on top of each other. That’s what this experiment turned out to be. The premise: Anthropic open-sourced a vulnerability discovery harness — a self-driving pipeline that spawns parallel agents inside gVisor-sandboxed containers, each one a claude -p headless session tasked with finding memory-safety bugs in C/C++ code. The pipeline is opinionated in a way that’s both admirable and limiting: it speaks Anthropic, it runs Claude, it requires an OAuth token or API key, and the agent container is a Node + npm install with the Anthropic CLI as the loop driver. ...
All 30 volumes of the Jìngdé Chuándēng Lù (景德傳燈錄, 1004 CE) translated into literary Thai, with deterministic quality scoring and content-addressed versioning. v0.1.27 is the current release: 30/30 volumes at 4.0+/4.0 quality, 807/807 segments pass the strict judge, published as bilingual PDFs on github.com/nbosa/jingde-chuandenglu-thai under CC0 1.0. ⚖️ What changed since June 15 (v0.3.0) The June 15 version of this page described a working draft (v0.3.0, 64% pass, vol04 only). The state on June 20 is different in three concrete ways: ...
I spent the last ten days asking a reasoning model to translate 30 volumes of classical Chinese Zen records into literary Thai. The work surfaced a dozen useful ideas, and exactly one bad one. The bad one is the reason I’m writing this. The good one is that translation quality, like security, is a property of a system, not a property of a prompt. ...
There’s a pattern that repeats itself in the history of computing, and we might be living through its AI equivalent right now. In the early CPU era, the benchmark that mattered was clock speed. Intel vs. AMD fought on megahertz, then gigahertz. Marketing budgets were built around single numbers. Consumers learned to equate “faster clock = better chip.” It was clean, legible, and — for a while — true. Then it stopped being true. The gains from raw frequency hit physical and thermodynamic walls. The industry pivoted almost overnight: instead of faster cores, build more cores. Parallelism became the new religion. ...