Simon Willison

节目介绍: 在这期节目中，我们深度剖析了知名开源项目 Datasette 作者 Simon Willison 的最新技术探索——如何利用 MicroPython 与 WebAssembly（WASM）打造一个安全、高效且资源受控的 Python 沙箱环境。文章详细揭示了这一方案如何解决传统沙箱难以克服的权限隔离、状态保持和计算资源限制等关键难题，尤其展示了 AI 助手在系统级原型开发中的创新应用，带来技术研发范式的深刻变革。 原文链接： https://simonwillison.net/2026/Jun/6/micropython-in-a-sandbox/#atom-everything 原文标题：Running Python code in a sandbox with MicroPython and WASM 主要内容： • 现有 Python 沙箱方案难以兼顾权限安全、资源限制和易用性，Simon Willison提出苛刻的设计需求。 • 采用 WebAssembly 结合轻量级 MicroPython 解释器，实现了高安全性且适合嵌入的沙箱环境。 • 利用 AI（GPT-5.5 Pro）辅助调研和开发，加速原型构建，展现“凭感觉编程”（vibe-coding）的新可能。 • 创新设计了跨沙箱边界的主机函数接口，实现了 Python 解释器状态的持久化和会话交互。 • 通过 wasmtime 的“燃料”机制严格控制 CPU 使用，防止无限循环等恶意行为导致资源耗尽。 推荐理由： 这篇文章不仅带来一套极具创新性的 Python 沙箱解决方案，更重要的是，它展示了 AI 助手如何融入系统级软件开发，极大提升了研发效率和原型迭代速度。对于关注安全隔离、资源控制以及动态语言沙箱技术的开发者和安全工程师而言，本文提供了宝贵的技术洞察和实践经验。作为「Andrej Karpathy的RSS订阅清单」的精选推荐，我们强烈鼓励您深入阅读原文，了解这一前沿技术如何在未来影响软件安全和云端插件生态。 --- 「Andrej Karpathy的RSS订阅清单」为您甄选全球最前沿的AI技术博客，深度剖析技术背后的核心洞察。 由 voieech.com 提供技术支持。

vibe coding 與 agentic engineering 在 Simon Willison 身上模糊了。他連 production code 都不再逐行 review，本文整理他的不安、guilt 與三條軟體可信度準則。 ⭐ 文章深度讀：完整原文與三條讀者帶得走的軟體可信度準則都在這篇 → https://heymaibao.com/simon-willison-stops-reviewing-production-code/ ⚡ 章節重點 開場：AI 鐵律被打破了 00:00 Simon 自承：兩條線開始模糊 00:47 罪惡感是專業底線 03:37 信任搬移的隱形代價 05:25 SDLC 上下游全在搬位置 07:15 三條新的可信度準則 08:29 📝 懶人包 ∙ Simon Willison 自承：在常見任務上，他連 production code 也已經不再逐行 review Claude Code 寫的東西。他用 disturbing、upsetting、guilt 這些字描述這個轉變。 ∙ 他把 agent 當成隔壁團隊交付的 service 在用：看文件、用、出問題才挖。但他承認 Claude Code 沒有 professional reputation，這個 gap 沒有解，只能靠「它一直做對」當代替品。 ∙ 他指出評估軟體的標準變了：commits、README、自動測試 30 分鐘可以合成，連他自己的項目都看不出來。退路是「有沒有人真的用過」，個人版用兩週、企業版兩家大公司用過六個月。 ∙ (諾特斯判斷) 這個重疊不是普世現象，是「資深工程師 + 高可靠 agent」這個特定組合下的個案。把 Simon 的 guilt 留著，比急著磨掉它安全很多。 📚 參考資料 Vibe coding and agentic engineering are starting to overlap → https://simonwillison.net/2026/May/6/vibe-coding-and-agentic-engineering/ Ep. #9, The AI Coding Paradigm Shift with Simon Willison → https://www.heavybit.com/library/podcasts/high-leverage/ep-9-the-ai-coding-paradigm-shift-with-simon-willison Not all AI-assisted programming is vibe coding (but vibe coding rocks) → https://simonwillison.net/2025/Mar/19/vibe-coding/ What is agentic engineering? → https://simonwillison.net/guides/agentic-engineering-patterns/what-is-agentic-engineering/

Podcast : Lenny's Podcast: Product | Career | Growth (LS 62 · TOP 0.1% what is this? ) Episode : An AI state of the union: We’ve passed the inflection point, dark factories are coming, and automation timelines | Simon Willison Pub date : 2026-04-02 Get Podcast Transcript → powered by Listen411 - fast audio-to-text and summarization Simon Willison is a prolific independent software developer, a blogger, and one of the most visible and trusted voices on the impact AI is having on builders. He co-created Django, the web framework that powers Instagram, Pinterest, and tens of thousands of other websites. He coined the term “prompt injection,” popularized the terms “AI slop” and “agentic engineering,” and has built over 100 open source projects, including Datasette, a data analysis tool used by investigative journalists worldwide. What makes Simon unique is that he’s made the leap from traditional software engineering to AI-native development more fully and visibly than almost anyone—and he’s been documenting everything he learns in real time on his blog, SimonWillison.net . In our in-depth conversation, Simon shares: 1. Why November 2025 was the inflection point when AI coding agents crossed from “mostly works” to “actually works” 2. How Simon writes 95% of his code from his phone now and why he’s mentally exhausted by 11 a.m. 3. Why mid-career engineers (not juniors) are most at risk right now 4. The three agentic engineering patterns Simon uses daily (red/green TDD, templates, hoarding) 5. The next leap: the “dark factory” pattern where nobody writes or reviews code and AI does its own QA 6. Why prompt injection is an unsolved security problem and the “lethal trifecta” that will likely lead to an AI Challenger disaster 7. Why the pelican riding a bicycle became the unofficial benchmark for AI model quality — Brought to you by: WorkOS —Modern identity platform for B2B SaaS, free up to 1 million MAUs Vanta —automate compliance, manage risk, and accelerate trust with AI — Episode transcript: https://www.lennysnewsletter.com/p/an-ai-state-of-the-union — Archive of all Lenny's Podcast transcripts: https://www.dropbox.com/scl/fo/yxi4s2w998p1gvtpu4193/AMdNPR8AOw0lMklwtnC0TrQ?rlkey=j06x0nipoti519e0xgm23zsn9&st=ahz0fj11&dl=0 — Where to find Simon Willison: • X: https://x.com/simonw • LinkedIn: https://www.linkedin.com/in/simonwillison • Website: <a href=

Simon Willison is a prolific independent software developer, a blogger, and one of the most visible and trusted voices on the impact AI is having on builders. He co-created Django, the web framework that powers Instagram, Pinterest, and tens of thousands of other websites. He coined the term “prompt injection,” popularized the terms “AI slop” and “agentic engineering,” and has built over 100 open source projects, including Datasette, a data analysis tool used by investigative journalists worldwide. What makes Simon unique is that he’s made the leap from traditional software engineering to AI-native development more fully and visibly than almost anyone—and he’s been documenting everything he learns in real time on his blog, SimonWillison.net . In our in-depth conversation, Simon shares: 1. Why November 2025 was the inflection point when AI coding agents crossed from “mostly works” to “actually works” 2. How Simon writes 95% of his code from his phone now and why he’s mentally exhausted by 11 a.m. 3. Why mid-career engineers (not juniors) are most at risk right now 4. The three agentic engineering patterns Simon uses daily (red/green TDD, templates, hoarding) 5. The next leap: the “dark factory” pattern where nobody writes or reviews code and AI does its own QA 6. Why prompt injection is an unsolved security problem and the “lethal trifecta” that will likely lead to an AI Challenger disaster 7. Why the pelican riding a bicycle became the unofficial benchmark for AI model quality — Brought to you by: WorkOS —Modern identity platform for B2B SaaS, free up to 1 million MAUs Vanta —automate compliance, manage risk, and accelerate trust with AI — Episode transcript: https://www.lennysnewsletter.com/p/an-ai-state-of-the-union — Archive of all Lenny's Podcast transcripts: https://www.dropbox.com/scl/fo/yxi4s2w998p1gvtpu4193/AMdNPR8AOw0lMklwtnC0TrQ?rlkey=j06x0nipoti519e0xgm23zsn9&st=ahz0fj11&dl=0 — Where to find Simon Willison: • X: https://x.com/simonw • LinkedIn: https://www.linkedin.com/in/simonwillison • Website: https://simonwillison.net • Agentic Engineering Patterns: https://simonwillison.net/guides/agentic-engineering-patterns — Where to find Lenny: • Newsletter: https://www.lennysnewsletter.com • X: https://twitter.com/lennysan • LinkedIn: https://www.linkedin.com/in/lennyrachitsky/ — In this episode, we cover: (00:00) Introduction to Simon Willison (02:40) The November 2025 inflection point (08:01) What’s possible now with AI coding (10:42) Vibe coding vs. agentic engineering (13:57) The dark-factory pattern (20:41) Where bottlenecks have shifted (23:36) Where human brains will continue to be valuable (25:32) Defending of software engineers (29:12) Why experien

AI Coding agent 讓寫程式成本趨近零，但 Simon Willison 指出好程式的成本沒有跟著降。他列出好程式的 9 個品質維度，解釋為什麼你每天做的工程決策需要重新校準。 ⭐ 文章深度讀：完整解析好程式的 9 個品質維度 → https://heymaibao.com/code-is-cheap-now/ 📚 參考資料 Writing code is cheap now - Agentic Engineering Patterns - Simon Willison's Weblog → https://simonwillison.net/guides/agentic-engineering-patterns/code-is-cheap/

In this milestone 150th episode, hosts Kelly Schuster-Paredes and Sean Tibor sit down with Simon Willison, co-creator of Django and creator of Datasette and LLM tools, for an in-depth conversation about artificial intelligence in Python education. The discussion covers the current landscape of LLMs in coding education, from the benefits of faster iteration cycles to the risks of students losing that crucial "aha moment" when they solve problems independently. Simon shares insights on prompt injection vulnerabilities, the importance of local models for privacy, and why he believes LLMs are much harder to use effectively than most people realize. Key topics include: Educational Strategy : When to introduce AI tools vs. building foundational skills first Security Concerns : Prompt injection attacks and their implications for educational tools Student Engagement : Maintaining motivation and problem-solving skills in an AI world Practical Applications : Using LLMs for code review, debugging, and rapid prototyping Privacy Issues : Understanding data collection and training practices of major AI companies Local Models : Running AI tools privately on personal devices The "Jagged Frontier" : Why LLMs excel at some tasks while failing at others Simon brings 20 years of Django experience and deep expertise in both web development and AI tooling to discuss how educators can thoughtfully integrate these powerful but unpredictable tools into their classrooms. The conversation balances excitement about AI's potential with realistic assessments of its limitations and risks. Whether you're a coding educator trying to navigate the AI revolution or a developer interested in the intersection of education and technology, this episode provides practical insights for working with LLMs responsibly and effectively. Resources mentioned: Simon's blog: simonwillison.net Mission Encodable curriculum Datasette and LLM tools GitHub Codespaces for safe AI experimentation Special Guest: Simon Willison. Support Teaching Python

It’s always a good day if you see a pelican. In Episode 30 of Talking Postgres with Claire Giordano , open source developer Simon Willison —creator of Datasette and co-creator of Django—joins to explore how AI is useful for data engineers today. We move past the hype and boosterism to dig into example after example: structured data extraction, alt text and accessibility, safety and security (aka the fiddly bits), and why Postgres’s fine-grained permissions are such a good fit for AI-powered workflows. Also: Pulitzer-worthy data tooling, the science fiction of the 10X engineer, agents, MCP, RAG, the multitude of models, and why Simon spends so many waking hours on the jagged frontier of AI. Links mentioned in this episode: Blog: Simon Willison’s Weblog Blog: Simon’s Willison’s TIL - Things I’ve Learned Podcast episode: Working in public on open source with Simon Willison and Marco Slot Project page: Django Web Framework Project page: Datasette , for finding stories in data GitHub repo: llm CLI tool and Python library Demo: Language models on the command-line w/ Simon Willison Blog post: OpenAI’s new open weight (Apache 2) models are really good , by Simon Willison Podcast episode: Accessibility and Gen AI podcast with guest Simon Willison Blog post: New dashboard: alt text for all my images , by Simon Willison Keynote talk: Big Opportunities in Small Data , by Simon Willison at Citus Con: An Event for Postgres 2023 Blog post: How OpenElections Uses LLMs , by Derek Willis Blog posts tagged with pelican-riding-a-bicycle on Simon Willison’s Weblog Blog post: No, AI is not Making Engineers 10x as Productive , via Colton Voege, featured on Simon’s weblog GitHub repo: pgvector extension to Postgres Cal invite: LIVE recording of Ep31 of Talking Postgres to happen on Wed Sep 17, 2025

He's one of the most thoughtful voices in the world of Artificial Intelligence. In this episode, “Truth of the Matter” host Natasha Zouves sits down with the pioneering technologist and co-creator of Django, Simon Willison. As AI accelerates at breakneck speed, Willison helps us cut through the hype to confront the real stakes: Which jobs are most at risk in this new era, and which might actually thrive? How do we “AI-proof” our own lives and careers when the ground is shifting under our feet? In this wide-ranging conversation, Willison pulls back the curtain on the future we’re building, often faster than we can fully understand it. From disinformation campaigns to automations’ quiet creep into white-collar work, he explains what keeps him up at night — and why the U.S. may be flying blind if global competitors like China reject regulatory guardrails. This is a frank, fascinating conversation about power, risk and the responsibility we all carry as we shape the future of intelligence itself. “The Truth of the Matter" podcast goes beyond the headlines to uncover the hidden stories shaping our world. These stories are more than just hidden truths—they’re blueprints for navigating our own lives, offering rare insights into the human experience and lessons learned. You can find “The Truth of the Matter” wherever you listen to your podcasts. Connect with host Natasha Zouves

In this episode we talked to Simon Willison. Simon is the creator of Datasette, an open source tool for exploring and publishing data. He currently works full-time building open source tools for data journalism, built around Datasette and SQLite. Prior to becoming an independent open source developer, Simon was an engineering director at Eventbrite. Simon joined Eventbrite through their acquisition of Lanyrd, a Y Combinator funded company he co-founded in 2010. He is a co-creator of the Django Web Framework, and has been blogging about web development and programming since 2002 at simonwillison.net We talked to Simon about his goal of building tools for data journalists, what he's learned about tinkering with, and writing about, AI models for years, his excitement about their code-generating capabilities, how to get the most out of all of these tools, and what generative AI tools have to do with pelicans. You can find Simon at https://simonwillison.net Please enjoy our conversation with Simon Willison! -- David's book, The Well-Grounded Data Analyst is out! ⁠https://www.manning.com/books/the-well-grounded-data-analyst⁠ If you want to find out more, we have a whole episode about it: ⁠https://open.spotify.com/episode/5D0iDtQRh3tWiIhokrjz3x?si=AiX6YyRET16lnzXDlvdcfw

OUTLINE: 00:00 Opening Teaser 00:36 Introduction 01:35 Working On Django 04:35 Future of Generative AI & Accessibility 07:23 Latest Tools & Models (Google Gemini Flash 2.0, Open AI, Video Streaming APIs, Amazon Nova) 11:39 Frontrunners of AI? 14:48 Daily Tools 19:14 LLM Command Line Tool 22:10 Using LLM For Alt Text For Images 24:58 Making LLM More Accessible 32:36 Will AI Replace Jobs? 39:50 The Dangers of AI 43:13 Launching Django 46:52 Datasette Open Source Tool 51:29 Developers Working With The Accessibility Community 57:34 Using NotebookLM To Prepare For This Podcast 1:00:43 Wrap Up -- EPISODE LINKS: Datasette https://datasette.io The Book on Accessibility by Charlie Triplett https://www.thebookonaccessibility.com Accessibility Acceptance Criteria https://www.magentaa11y.com NotebookLM https://notebooklm.google Simon Willison's Blog https://simonwillison.net Simon Willison's Social Media https://x.com/simonw https://bsky.app/profile/simonwillison.net

Podcast : The Real Python Podcast (LS 48 · TOP 1% what is this? ) Episode : Simon Willison: Using LLMs for Python Development Pub date : 2025-01-24 Get Podcast Transcript → powered by Listen411 - fast audio-to-text and summarization What are the current large language model (LLM) tools you can use to develop Python? What prompting techniques and strategies produce better results? This week on the show, we speak with Simon Willison about his LLM research and his exploration of writing Python code with these rapidly evolving tools. Simon has been researching LLMs over the past two and a half years and documenting the results on his blog. He shares which models work best for writing Python versus JavaScript and compares coding tools and environments. We discuss prompt engineering techniques and the first steps to take. Simon shares his enthusiasm for the usefulness of LLMs but cautions about the potential pitfalls. Simon also shares how he got involved in open-source development and Django. He’s a proponent of starting a blog and shares how it opened doors for his career. This episode is sponsored by Postman. Course Spotlight: Advanced Python import Techniques The Python import system is as powerful as it is useful. In this in-depth video course, you’ll learn how to harness this power to improve the structure and maintainability of your code. Topics: 00:00:00 – Introduction 00:02:38 – How did you get involved in open source? 00:04:04 – Writing an XML-RPC library 00:04:40 – Working on Django in Lawrence, Kansas 00:05:31 – Started building open-source collection 00:06:52 – shot-scraper: taking automated screenshots of websites 00:08:09 – First experiences with LLMs 00:10:08 – 22 years of simonwillison.net 00:18:22 – Navigating the hype and criticism of LLMs 00:22:14 – Where to start with Python code and LLMs? 00:26:22 – Sponsor: Postman 00:27:13 – ChatGPT Canvas vs Code Interpreter 00:28:23 – Asking nicely, tricking the system, and tipping? 00:30:35 – More Code Interpreter and building a C extension 00:32:05 – More details on Canvas 00:36:55 – What is a workflow for developing using LLMs? 00:39:43 – Creating pieces of code vs a system 00:42:00 – Workout program for prompting and pitfalls 00:53:54 – Video Course Spotlight 00:55:14 – Why an SVG of a pelican riding a bicycle? 00:57:48 – Repeating a query and refining 01:03:00 – Working in an IDE or text editor 01:05:45 – David Crawshaw on writing code with LLMs 01:08:33 – Running an LLM locally to write code 01:14:02 – Staying out of the AGI conversation 01:16:07 – What are you excited about in the world of Python? 01:18:34 – What do you want to learn next? 01:19:53 – How can people follow your work online? 01:20:51 – Thanks and goodbye Show Links: Simon Willison’s Weblog </l

Adam Davidson welcomes listeners to a thought-provoking conversation with Simon Willison, a feedforward expert, as they delve into the intricate relationship between AI and security. Their discussion opens with a humorous yet intriguing benchmark—Simon’s whimsical challenge of generating an SVG of a pelican riding a bicycle, which serves as a metaphor for evaluating AI models. This playful examination leads to deeper concerns around the safety and reliability of AI usage, especially within enterprise contexts. Simon articulates the anxieties many organizations face regarding data privacy and the potential risks associated with feeding sensitive information into AI chatbots. A central theme that emerges is the misconception that AI models retain user input in a way that would jeopardize confidential data. Simon clarifies that while the models do not learn from individual user interactions in real-time, there are still significant complexities around data handling and how different AI providers manage user inputs for future training. Takeaways: Understanding the implications of prompt injection is crucial for developers using AI models. AI models are very gullible, which can lead to serious security vulnerabilities. Using local models can mitigate risks associated with data leaving your organization. Open source models are becoming more capable and accessible for organizations concerned about privacy. Jailbreaking models can expose vulnerabilities, but they often lead to harmless outcomes. Security measures should focus on limiting the impact of potential exploits in AI applications. Links referenced in this episode: SimonWillison.net Companies mentioned in this episode: FeedForward SimonWillison.net OpenAI Anthropic Google AWS Nvidia Alibaba