LecturaInvestigaciónRadarMarco de inversión
Iniciar sesión / Registrarse
← Volver a la lectura
NoticiasTema · Claude CodeMaterial2 min de lecturaEditorial de DisconfirmAI

Django Co-creator Simon Willison: Claude Code Ran for 12 Hours to Produce a Complete SPARQL Implementation, But I Can’t Review It

Django co-creator and Datasette creator Simon Willison conducted an experiment using Claude Code’s Ultracode mode: he issued a prompt containing a typo, allowing the AI agent to run continuously for over 12 hours, ultimately producing a SPARQL SQLite extension that passed 636 W3C tests. He acknowledged that the codebase had exceeded his capacity for manual review, thereby questioning: if he cannot understand the output, how much value does this achievement hold for him?

2026-10-16 09:58 GMT+8

Simon Willison sent a prompt to Claude Code’s Ultracode mode with the intention of having the extension "hit the data rows directly," but accidentally typed "delete rows" on his phone. This instruction, containing a typo, caused Claude Code to run continuously for over 12 hours, ultimately producing a complete implementation of SPARQL 1.1—sparqlite, a loadable SQLite extension written in Rust that natively executes SPARQL queries and updates within the SQLite process.

The Ultracode mode works by generating JavaScript to define and coordinate a network of subagents, each handling different parts of complex problems. sparqlite employs integer-encoded terms, covering indexes, a cost-based query planner, batched joins, and an optional direct SQLite B-tree reader; it is 3.5 times faster than SQL translation schemes in count mode and 2.8 times faster when returning full results, passing 636 of the 639 applicable W3C evaluation tests.

When Willison checked on the progress the next day, he found that the AI had built a substantial number of Rust crates, so he added a follow-up prompt requesting that every crate directory include a README, a tutorial.md teaching users how to install the extension and run SPARQL in the SQLite command line, and a script to populate realistic example data. He concluded: "This feels like next-level vibe coding—the produced code is not remotely feasible to review line-by-line, and even following the documentation is a significant investment of work. I now have a full SPARQL implementation inside SQLite, but if I created it on a whim and can't (or won't) invest the necessary time to understand what it can do, how valuable is it to me?"

Iniciar sesión / Registrarse
LecturaInvestigaciónRadarMarco de inversión

Fuentes

  • simonwillison.netSimon Willison’s Weblog↗
Tema

Claude Code

Django联合创始人Simon Willison利用Claude Code的Ultracode模式,通过一条含拼写错误的提示词,让AI代理连续运行超过12小时,生成了名为sparqlite的Rust语言SQLite扩展。该工具实现了SPA…

2 pasos1 piezasActualizado 2026-11-02 06:01

Cómo llegó hasta aquí

  1. 2026-10-16Simon Willison在博客发布实验结果,描述使用Claude Code Ultracode模式生成sparqlite的过程及代码不可审查的困境。simonwillison.net ↗
  2. 2026-10-16Lilith AI等媒体跟进报道,强调该项目由单一提示词触发,耗时12小时,且所有文档和代码均由LLM编写。lilithai.dev ↗

Lo que aún está pendiente

  • 独立开发者或RDF社区是否会尝试部署sparqlite并验证其性能数据?
  • 在缺乏人类代码审查的情况下,如何界定此类AI生成数据库引擎的安全责任归属?
Leer el tema completo →
Continuar investigando →