Simon WillisonEvery podcast appearance, updated as new ones drop

On episode 9 of High Leverage, Joe Ruscio sits down with Simon Willison to unpack the rapid evolution of AI coding tools and what they mean for software development. They explore the shift from vibe coding to agentic engineering, how coding agents are reshaping workflows, and why experience still matters. The conversation dives into trust, security, and what breaks when code becomes cheap. The post appeared first on Heavybit .

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

Time for the annual predictions episode! Bryan and Adam were joined by frequent future-ologists Simon Willison, Steve Klabnik, and Ian Grunert to review past predictions and peer into the future. If any of these predictions come to fruition, it's going to be an interest 1, 3, or 6 years! In addition to Bryan Cantrill and Adam Leventhal , speakers included Simon Willison , Steve Klabnik , and Ian Grunert . Previously on Oxide and Friends: OxF s04e02 – Open Source LLMs with Simon Willison OxF s02e23 – Predictions 2022 OxF s03e20 – Predictions 2023! OxF s04e01 – Predictions 2024! OxF s05e01 – Predictions 2025 Predictions during the show: Adam 1 year: AI companies go on an acquisition binge (especially for anything that smells like data) 3 year: Crisis of AI slop open source (both projects and contributions) 6 year: Jensen hands over the reins at Nvidia 6 year: Tesla is out of the consumer car business 6 year: With the iPhone market shrinking, Apple has several new attempts at the next potential flagship product Bryan 1 year: "Vibe coding" is out of the lexicon -- or used strictly pejoratively it becomes a named condition (for which Adam -- in an act of nomenclature genius rivaling The Leventhal Conundrum -- suggested "Deep Blue") 1 year: A frontier model company has a prominent whitepaper making the case that AI will lead to broad-based prosperity rather than job loss 1 year: Harvey.ai becomes the pets.com of the AI boom -- and a harbinger of the coming bust (which becomes known as a Correction-like euphemism) 1 year: A prominent S1 has revalations of economic behavior that has an effect beyond the company's IPO 3 year: Frontier models treat AGI as "already done" -- and ASI as a non-goal 3 year: Custom-written software thrives in lieu of SaaS 6 year: DSM adds LLMs as a substance that can induce psychosis 6 year: $NVDA not beyond its November 2025 peak Simon 1 year: The AI for programming holdouts are going to have a nasty shock 1 year: We're going to solve sandboxing 1 year: Our own challenger disaster with respect to coding agent security - see the Normalization of Deviance in AI by Johann Rehberger 3 year: Something that seems impossible for a coding agent to build today - like a full working web browser - won't just be built by coding agents, it will be unsurprising 3 year: We will find out if the Jevons paradox saves our careers as software engineers or not 6 year: The number of people employed to type code into computers will drop to almost nothing - it will be like punch card operators. Those of us who write code today will have very different jobs that still build software and take advantage of our previous coding experience. Steve 1 year: Agent Orchestration will still be a hot topic. It'll be partially, but not entirely, solved. Updated with some more rigour: We won't have a "kubernetes for

In episode 2 of Data Renegades, CL Kao and Dori Wilson speak with Simon Willison. Together they dive into the origins of Datasette, the evolution of data journalism, and the surprising ways open source tools shape global reporting. Simon also explains how LLM-based agents will redefine data cleaning, enrichment, and analysis. A must-listen for anyone building or scaling data teams. The post appeared first on Heavybit .

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

On this episode of Screaming in the Cloud , Corey Quinn talks with Simon Willison, founder of Datasette and creator of LLM CLI about AI’s realities versus the hype. They dive into Simon’s “lethal trifecta” of AI security risks, his prediction of a major breach within six months, and real-world use cases of his open source tools, from investigative journalism to OSINT sleuthing. Simon shares grounded insights on coding with AI, the real environmental impact, AGI skepticism, and why human expertise still matters. A candid, hype-free take from someone who truly knows the space. Highlights : 00:00 Introduction and Security Concerns 02:32 Conversations and Kindness 04:56 Niche Museums and Collecting 06:52 Blogging as a Superpower 08:01 Challenges of Writing and AI 15:08 Unique Use Cases of Dataset 19:33 The Evolution of Open Source 21:09 Security Vulnerabilities in AI 32:18 Future of AI and AGI Concerns 37:10 Learning Programming with AI 39:12 Vibe Coding and Its Risks 41:49 Environmental Impact of AI 46:34 AI in Legal and Creative Fields 54:20 Voice AI and Ethical Concerns 01:00:07 Monetizing Content Creatively Links: Simon Willison’s Blog Datasette Project LLM command-line tool and Python library Niche Museums GitHub MCP prompt injection example Highlights from the Claude 4 system prompt AI energy usage tag AI assisted search-based research actually works now POSSE: Publish on your own site, syndicate elsewhere Bellingcat Lawyer cites fake cases invented by ChatGPT, judge is not amused (May 2023) AI hallucination cases database Sponsor Simon to get his monthly summary newsletter https://simonwillison.net/ https://www.linkedin.com/in/simonwillison https://datasette.io/ Sponsor Augment Code: https://www.augmentcode.com/

In episode 39 of Generationship, Rachel speaks with Simon Willison, founder of Datasette and co-creator of Django. Simon discusses the surprising resurgence of blogging, his coining of the term “prompt injection,” the power of learning in public, and how he uses GitHub issues as an external brain to manage hundreds of projects. This quick-witted and humorous conversation offers a pragmatic look at leveraging today's tools for maximum productivity and impact. The post appeared first on Heavybit .

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, “Truth of the Matter” host Natasha Zouves sits down with Simon Willison — pioneering technologist, co-creator of Django, and one of the most thoughtful voices in the world of Artificial Intelligence. 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. NewsNation’s series “The Truth of the Matter 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: / natashazouves Producer: Ryan KerrNewsNation is your source for fact-based, unbiased news for all America. More from NewsNation: https://www.newsnationnow.com/ Get our app: https://trib.al/TBXgYpp Find us on cable: https://trib.al/YDOpGyG How to watch on TV or streaming: https://trib.al/ V

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

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

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 shot-scraper Matt’s Script Archive, Inc. - Free Perl CGI Scripts XR - my XML-RPC library, now in WordPress - GitHub Adrian Holovaty advertises for someone to join him working in Lawrence (May 2003) - Holovaty.com Datasette: An open source multi-tool for exploring and publishing data My SQLite tag page - Simon Willison Chatbot Arena: Free AI Chat to Compare & Test Best AI Chatbots DeepSeek v3 notes on Ch

Due to overwhelming demand (>15x applications:slots), we are closing CFPs for AI Engineer Summit NYC today. Last call! Thanks, we’ll be reaching out to all shortly! The world’s top AI blogger and friend of every pod, Simon Willison, dropped a monster 2024 recap: Things we learned about LLMs in 2024 . Brian of the excellent TechMeme Ride Home pinged us for a connection and a special crossover episode, our first in 2025. The target audience for this podcast is a tech-literate, but non-technical one. You can see Simon’s notes for AI Engineers in his World’s Fair Keynote . Timestamp * 00:00 Introduction and Guest Welcome * 01:06 State of AI in 2025 * 01:43 Advancements in AI Models * 03:59 Cost Efficiency in AI * 06:16 Challenges and Competition in AI * 17:15 AI Agents and Their Limitations * 26:12 Multimodal AI and Future Prospects * 35:29 Exploring Video Avatar Companies * 36:24 AI Influencers and Their Future * 37:12 Simplifying Content Creation with AI * 38:30 The Importance of Credibility in AI * 41:36 The Future of LLM User Interfaces * 48:58 Local LLMs: A Growing Interest * 01:07:22 AI Wearables: The Next Big Thing * 01:10:16 Wrapping Up and Final Thoughts Transcript [00:00:00] Introduction and Guest Welcome [00:00:00] Brian: Welcome to the first bonus episode of the Tech Meme Write Home for the year 2025. I'm your host as always, Brian McCullough. Listeners to the pod over the last year know that I have made a habit of quoting from Simon Willison when new stuff happens in AI from his blog. Simon has been, become a go to for many folks in terms of, you know, Analyzing things, criticizing things in the AI space. [00:00:33] Brian: I've wanted to talk to you for a long time, Simon. So thank you for coming on the show. No, it's a privilege to be here. And the person that made this connection happen is our friend Swyx, who has been on the show back, even going back to the, the Twitter Spaces days but also an AI guru in, in their own right Swyx, thanks for coming on the show also. [00:00:54] swyx (2): Thanks. I'm happy to be on and have been a regular listener, so just happy to [00:01:00] contribute as well. [00:01:00] Brian: And a good friend of the pod, as they say. Alright, let's go right into it. [00:01:06] State of AI in 2025 [00:01:06] Brian: Simon, I'm going to do the most unfair, broad question first, so let's get it out of the way. The year 2025. Broadly, what is the state of AI as we begin this year? [00:01:20] Brian: Whatever you want to say, I don't want to lead the witness. [00:01:22] Simon: Wow. So many things, right? I mean, the big thing is everything's got really good and fast and cheap. Like, that was the trend throughout all of 2024. The good models got so much cheaper, they got so much faster, they got multimodal, right? The image stuff isn't even a surprise anymore. [00:01:39] Simon: They're growing video, all of that kind of stuff. So that's all really exciting. [00:01:43] Advancements in AI Models [00:01:43] Simon: At the same time, they didn't get massively better than GPT 4, which was a bit of a surprise. So that's sort of one of the open questions is, are we going to see huge, but I kind of feel like that's a bit of a distraction because GPT 4, but way cheaper, much larger context lengths, and it [00:

The great Simon Willison joins SWYX and I to talk about everything we learned about LLMs in 2024, and what the state of AI is generally, as we go into 2025. Here is Simon's blog post we keep referring to: https://simonwillison.net/2024/Dec/31... 00:00 The State of AI in 2025 10:05 The Evolution of AI Models 19:54 Challenges in AI Agents 30:07 The Future of AI in Creative Industries 38:29 The Rise of AI Influencers 40:54 Credibility in the Age of AI 43:15 The Future of User Interfaces for LLMs 51:17 Local LLMs and Desktop AI Applications 55:17 AI Tools and Applications for Everyday Use 01:01:26 The Future of OpenAI and AI Regulation 01:08:08 The Need for Better Criticism of LLMs 01:10:41 The Future of Wearables and AI Integration See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info .

In this conversation, Simon Willison discusses the intersection of AI, Open Source, and journalism, emphasizing the importance of tools like Dataset in enhancing data journalism. He reflects on his journey from developing Django to his current work with AI, highlighting the role of open source in software development. Willison shares insights on how AI can augment human capabilities rather than replace them, and he expresses concerns about the future of AI, particularly regarding AGI. The discussion also touches on the evolving landscape of programming and the need for better onboarding processes for new developers.

Hey all, Alex here, coming to you from the (surprisingly) sunny Seattle, with just a mind-boggling week of releases. Really, just on Tuesday there was so much news already! I had to post a recap thread , something I do usually after I finish ThursdAI! From Anthropic reclaiming close-second sometimes-first AI lab position + giving Claude the wheel in the form of computer use powers, to more than 3 AI video generation updates with open source ones, to Apple updating Apple Intelligence beta, it's honestly been very hard to keep up, and again, this is literally part of my job! But once again I'm glad that we were able to cover this in ~2hrs, including multiple interviews with returning co-hosts ( Simon Willison came back, Killian came back) so definitely if you're only a reader at this point, listen to the show ! Ok as always (recently) the TL;DR and show notes at the bottom (I'm trying to get you to scroll through ha, is it working?) so grab a bucket of popcorn, let's dive in 👇 ThursdAI - Recaps of the most high signal AI weekly spaces is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Claude's Big Week: Computer Control, Code Wizardry, and the Mysterious Case of the Missing Opus Anthropic dominated the headlines this week with a flurry of updates and announcements. Let's start with the new Claude Sonnet 3.5 (really, they didn't update the version number, it's still 3.5 tho a different API model) Claude Sonnet 3.5: Coding Prodigy or Benchmark Buster? The new Sonnet model shows impressive results on coding benchmarks, surpassing even OpenAI's O1 preview on some. "It absolutely crushes coding benchmarks like Aider and Swe-bench verified," I exclaimed on the show. But a closer look reveals a more nuanced picture. Mixed results on other benchmarks indicate that Sonnet 3.5 might not be the universal champion some anticipated. My friend who has held back internal benchmarks was disappointed highlighting weaknesses in scientific reasoning and certain writing tasks. Some folks are seeing it being lazy-er for some full code completion, while the context window is now doubled from 4K to 8K! This goes to show again, that benchmarks don't tell the full story, so we wait for LMArena (formerly LMSys Arena) and the vibe checks from across the community. However it absolutely dominates in code tasks, that much is clear already. This is a screenshot of the new model on Aider code editing benchmark, a fairly reliable way to judge models code output, they also have a code refactoring benchmark Haiku 3.5 and the Vanishing Opus: Anthropic's Cryptic Clues Further adding to the intrigue, Anthropic announced Claude 3.5 Haiku! They usually provide immediate access, but Haiku remains elusive, saying that it's available by end of the month, which is very very soon. Making things even more curious, their highly anticipated Opus model has seemingly vanished from their website. "They've gone completely silent on 3.5 Opus," Simon Willison ( 𝕏 ) noted, mentioning conspiracy theories that this new Sonnet might simply be a rebranded Opus? 🕯️ 🕯️ We'll make a summoning circle for new Opus and update you once it lands (maybe next year) Claude Takes Control (Sort Of): Computer Use API and the Dawn of AI Agents ( 𝕏 ) The biggest bombshell this week? Anthropic's Computer Use. This isn't just about executing code; it’s about Claude interacti

The first episode of The Pragmatic Engineer Podcast is out. Expect similar episodes every other Wednesday. You can add the podcast in your favorite podcast player, and have future episodes downloaded automatically. Listen now on Apple , Spotify , and YouTube . Brought to you by: • Codeium : ​​ Join the 700K+ developers using the IT-approved AI-powered code assistant. • TLDR : Keep up with tech in 5 minutes — On the first episode of the Pragmatic Engineer Podcast, I am joined by Simon Willison. Simon is one of the best-known software engineers experimenting with LLMs to boost his own productivity: he’s been doing this for more than three years, blogging about it in the open. Simon is the creator of Datasette, an open-source tool for exploring and publishing data. He works full-time developing open-source tools for data journalism, centered on Datasette and SQLite. Previously, he was an engineering director at Eventbrite, joining through the acquisition of Lanyrd, a Y Combinator startup he co-founded in 2010. Simon is also a co-creator of the Django Web Framework. He has been blogging about web development since the early 2000s. In today’s conversation, we dive deep into the realm of Gen AI and talk about the following: • Simon’s initial experiments with LLMs and coding tools • Why fine-tuning is generally a waste of time—and when it’s not • RAG: an overview • Interacting with GPTs voice mode • Simon’s day-to-day LLM stack • Common misconceptions about LLMs and ethical gray areas • How Simon’s productivity has increased and his generally optimistic view on these tools • Tips, tricks, and hacks for interacting with GenAI tools • And more! I hope you enjoy this episode. — In this episode, we cover: (02:15) Welcome (05:28) Simon’s ‘scary’ experience with ChatGPT (10:58) Simon’s initial experiments with LLMs and coding tools (12:21) The languages that LLMs excel at (14:50) To start LLMs by understanding the theory, or by playing around? (16:35) Fine-tuning: what it is, and why it’s mostly a waste of time (18:03) Where fine-tuning works (18:31) RAG: an explanation (21:34) The expense of running testing on AI (23:15) Simon’s current AI stack (29:55) Common misconceptions about using LLM tools (30:09) Simon’s stack – continued (32:51) Learnings from running local models (33:56) The impact of Firebug and the introduction of open-source (39:42) How Simon’s productivity has increased using LLM tools (41:55) Why most people should limit themselves to 3-4 programming languages (45:18) Addressing ethical issues and resistance to using generative AI (49:11) Are LLMs are plateauing? Is AGI overhyped? (55:45) Coding vs. professional coding, looking ahead (57:27) The importance of systems thinking for software engineers (1:01:00) Simon’s advice for experienced engineers (1:06:29) Rapid-fire questions — Where to find Simon Willison: • X: https://x.com/simonw • LinkedIn: https://www.linkedin.com/in/simonwillison/ • Website

Today, we're joined by Simon Willison, independent researcher and creator of Datasette to discuss the many ways software developers and engineers can take advantage of large language models (LLMs) to boost their productivity. We dig into Simon’s own workflows and how he uses popular models like ChatGPT and Anthropic’s Claude to write and test hundreds of lines of code while out walking his dog. We review Simon’s favorite prompting and debugging techniques, his strategies for sidestepping the limitations of contemporary models, how he uses Claude’s Artifacts feature for rapid prototyping, his thoughts on the use and impact of vision models, the role he sees for open source models and local LLMs, and much more. The complete show notes for this episode can be found at https://twimlai.com/go/701 .

Known for co-creating Django and Datasette, as well as his thoughtful writing on LLMs, Simon Willison joins the show to chat about blogging as an accountability mechanism, how to build intuition with LLMs, building a startup with his partner on their honeymoon, and more. Segments: (00:00:00) The weird intern (00:01:50) The early days of LLMs (00:04:59) Blogging as an accountability mechanism (00:09:24) The low-pressure approach to blogging (00:11:47) GitHub issues as a system of records (00:16:15) Temporal documentation and design docs (00:18:19) GitHub issues for team collaboration (00:21:53) Copy-paste as an API (00:26:54) Observable notebooks (00:28:50) pip install LLM (00:32:26) The evolution of using LLMs daily (00:34:47) Building intuition with LLMs (00:43:24) Democratizing access to automation (00:47:45) Alternative interfaces for language models (00:53:39) Is prompt engineering really engineering? (00:58:39) The frustrations of working with LLMs (01:01:59) Structured data extraction with LLMs (01:06:08) How Simon would go about building a LLM app (01:09:49) LLMs making developers more ambitious (01:13:32) Typical workflow with LLMs (01:19:58) Vibes-based evaluation (01:23:25) Staying up-to-date with LLMs (01:27:49) The impact of LLMs on new programmers (01:29:37) The rise of 'Goop' and the future of software development (01:40:20) Being an independent developer (01:42:26) Staying focused and accountable (01:47:30) Building a startup with your partner on the honeymoon (01:51:30) The responsibility of AI practitioners (01:53:07) The hidden dangers of prompt injection (01:53:44) “Artificial intelligence” is really “imitation intelligence” Show Notes: Simon’s blog: https://simonwillison.net/ Natalie’s post on them building a startup together: https://blog.natbat.net/post/61658401806/lanyrd-from-idea-to-exit Simon’s talk from DjangoCon: https://www.youtube.com/watch?v=GLkRK2rJGB0 Simon on twitter: https://x.com/simonw Datasette: https://github.com/simonw/datasette Stay in touch: 👋 Make Ronak’s day by leaving us a review and let us know who we should talk to next! hello@softwaremisadventures.com Music: Vlad Gluschenko — Forest License: Creative Commons Attribution 3.0 Unported: https://creativecommons.org/licenses/by/3.0/deed.en

Simon Willison’s Weblog Datasette Datasette Cloud running on Fly.io Choose Boring Technology Datasette enrichments LLM and LLM plugins Mistral, Mixtral, and ways to run it on LLM NYT lawsuit against OpenAI ChatGPT for AppleScript Simon uses https://llm.mlc.ai/#ios to run Mistral 7B on his iPhone Building a Blog in Django Simon’s 15-year-old single file Django attempt djng and notes AI Superpowers book Support the Show LearnDjango.com Button Django News newsletter

Simon Willison joined Bryan and Adam to discuss a recent article maligning open source large language models. Simon has so much practical experience with LLMs, and brings so much clarity to what they can and can’t do. How do these systems work? How do they break? What are open and proprietary LLMs out there? Recorded 1/15/2024 We've been hosting a live show weekly on Mondays at 5p for about an hour, and recording them all; here is the recording . In addition to Bryan Cantrill and Adam Leventhal , we were joined by special guest Simon Willison . Some of the topics we hit on, in the order that we hit them: IEEE Spectrum: Open-Source AI Is Uniquely Dangerous Newsroom Robots with Simon Willison OxF: Another LPC55 ROM Vulnerability Simon Willison: Stuff we figured out about AI in 2023 llama.cpp Mistral AI France’s Mistral AI blows in with a $113M seed round at a $260M valuation to take on OpenAI Simon again: The AI trust crisis Reply All: Is Facebook Spying on You? Universal and Transferable Adversarial Attacks on Aligned Language Models New York Times Sues OpenAI Lycos ChatGPT Can Be Broken by Entering These Strange Words, And Nobody Is Sure Why Simon posted a follow up blog article where he explains using MacWhisper and Claude to make his LLM pull out a few of his favorite quotes from this episode: Talking about Open Source LLMs on Oxide and Friends If we got something wrong or missed something, please file a PR! Our next show will likely be on Monday at 5p Pacific Time on our Discord server; stay tuned to our Mastodon feeds for details, or subscribe to this calendar . We'd love to have you join us, as we always love to hear from new speakers!

Kate Holterhoff, analyst with Redmonk, and Simon Willison, founder of Dattasette, co-creator of Django, and expert in AI technologies, speak about the AI prompt injection vulnerability. Simon lays out what prompt injection is and why it is so difficult to mitigate. They also cover major industry players (OpenAI, Meta, Anthropic, Google), and the common mistake of confusing moderation, in the sense of not letting the model say bad things, with security, not letting an attack trigger the model into performing an action that leaks private data or triggers tools in the wrong way. Prompt injection is a security issue, and not one that can be solved through moderation alone. This RedMonk Conversation was published in video form on December 20, 2023.

In this episode of ByteSized RSE I talk about Django, a Python based web development framework that was developed in the mid 2000s. My guests are Tom Couch from the University College London and Max Albert from Southampton University. Links: https://www.djangoproject.com the entry point for Django with tutorials and references https://www.dj4e.com Django for you tutorial site https://www.feldroy.com/books/two-scoops-of-django-3-x the Book Two Scoops of Django by David Greenfeld https://pydanny.blogspot.com and here is his blog https://2024.djangocon.eu If you want to go to a Django conference - here is one... https://django-crispy-forms.readthedocs.io/en/latest/ Crispy forms in Django https://cookiecutter-django.readthedocs.io/en/latest/ Cookie Cutter Django https://medium.com/@devsumitg/how-to-connect-reactjs-django-framework-c5ba268cb8be an article how to connect ReactJS with Django Trivia https://www.holovaty.com Adrian Holovaty gave Django the name - apart from an engineer he is also a talented musician https://www.quora.com/What-is-the-history-of-the-Django-web-framework-Why-has-it-been-described-as-developed-in-a-newsroom/answer/Simon-Willison an interview with Simon Willison on how Django got created https://simonwillison.net Simon is co-creator of Django https://web.archive.org/web/20140716123229/https://docs.djangoproject.com/en/dev/internals/committers/ a brief history of the first Django committers https://archive.org/details/django-reinhardt/107-django_reinhardt-djangos_blues.mp3 The MP3 file of the music played in the episode. 1947, Django Blues by Django Reinhardt Byte-sized RSE is presented in collaboration with the UNIVERSE-HPC project. https://www.imperial.ac.uk/computational-methods/rse/events/byte-sized-rse/ ByteSized RSE link to Imperial College Get in touch Thank you for listening! Merci de votre écoute! Vielen Dank für´s Zuhören! Contact Details/ Coordonnées / Kontakt: Email mailto: peter@code4thought.org UK RSE Slack (ukrse.slack.com): @code4thought or @piddie Bluesky: https://bsky.app/profile/code4thought.bsky.social LinkedIn: https://www.linkedin.com/in/pweschmidt/ (personal Profile) LinkedIn: https://www.linkedin.com/company/codeforthought/ (Code for Thought Profile) This podcast is licensed under the Creative Commons Licence: https://creativecommons.org/licenses/by-sa/4.0/

In this second part of the episode with Simon Willison, he shares how Datasette , the open-source data exploration and publishing tool he built, could help journalists perform data analysis with minimum technical expertise. He also shares some fun use cases of ChatGPT in his personal life. Simon, a former software architect at The Guardian and a JSK Journalism Fellow at Stanford University, currently works full-time to build open-source tools for data journalism. Before becoming an independent open-source developer, Simon was an engineering director at Eventbrite. He is also renowned for his work as the co-creator of the Django Web Framework, a key tool in Python web development. If you're intrigued to discover how Datasette works and how it can help you in your newsroom, don't miss the opportunity to connect directly with Simon Willison. 🎧 Tune in to hear how AI has the potential to help amplify data journalism 🔔 Course registration is now open. Sign up for Wonder Tools X Newsroom Robots Generative AI for Media Pros Masterclass. A Live Cohort-Based Course taught by Jeremy Caplan & Nikita Roy. Sign up here . Hosted on Acast. See acast.com/privacy for more information.

Simon Willison, the creator of the open source data exploration and publishing tool Datasette , joins Nikita Roy to discuss the recent turmoil at Open AI and the new features unveiled at OpenAI’s first developer conference earlier this month.They discuss the security risks inherent in generative AI applications and explore the usefulness of small language models for journalists, particularly for analyzing sensitive data on personal devices. Simon , a former software architect at The Guardian and JSK Fellow at Stanford University, currently works full-time to build open-source tools for data journalism. Prior to becoming an independent open source developer, Simon served as an engineering director at Eventbrite. He is also renowned for his work as the co-creator of the Django Web Framework, a key tool in Python web development. 🎧Tune in for a detailed exploration of the latest features from OpenAI 🔔 Course registration is now open. Sign up for Wonder Tools X Newsroom Robots Generative AI for Media Pros Masterclass. A Live Cohort-Based Course taught by Jeremy Caplan & Nikita Roy. Sign up here . ✉️ Newsroom Robots now has a newsletter! Sign up here . Hosted on Acast. See acast.com/privacy for more information.

Send us Fan Mail Django co-creator Simon Willison joins to talk about large language models. A guide to large language models OpenAI Clip Datasette Join the Discord Follow us on Mastodon: Rooftop Ruby Collin Joel Show art created by JD Davis .

Code Interpreter is GA! As we do with breaking news, we convened an emergency pod and >17,000 people tuned in, by far our most biggest ever. This is a 2-for-1 post - a longform essay with our trademark executive summary and core insights - and a podcast capturing day-after reactions. Don’t miss either of them! Essay and transcript: https://latent.space/p/code-interpreter Podcast Timestamps [00:00:00] Intro - Simon and Alex [00:07:40] Code Interpreter for Edge Cases [00:08:59] Code Interpreter's Dependencies - Tesseract, Tensorflow [00:09:46] Code Interpreter Limitations [00:10:16] Uploading Deno, Lua, and other Python Packages to Code Interpreter [00:11:46] Code Interpreter Timeouts and Environment Resets [00:13:59] Code Interpreter for Refactoring [00:15:12] Code Interpreter Context Window [00:15:34] Uploading git repos [00:16:17] Code Interpreter Security [00:18:57] Jailbreaking [00:19:54] Code Interpreter cannot call GPT APIs [00:21:45] Hallucinating Lack of Capability [00:22:27] Code Interpreter Installed Libraries and Capabilities [00:23:44] Code Interpreter generating interactive diagrams [00:25:04] Code Interpreter has Torch and Torchaudio [00:25:49] Code Interpreter for video editing [00:27:14] Code Interpreter for Data Analysis [00:28:14] Simon's Whole Foods Crime Analysis [00:31:29] Code Interpreter Network Access [00:33:28] System Prompt for Code Interpreter [00:35:12] Subprocess run in Code Interpreter [00:36:57] Code Interpreter for Microbenchmarks [00:37:30] System Specs of Code Interpreter [00:38:18] PyTorch in Code Interpreter [00:39:35] How to obtain Code Interpreter RAM [00:40:47] Code Interpreter for Face Detection [00:42:56] Code Interpreter yielding for Human Input [00:43:56] Tip: Ask for multiple options [00:44:37] The Masculine Urge to Start a Vector DB Startup [00:46:00] Extracting tokens from the Code Interpreter environment? [00:47:07] Clientside Clues for Code Interpreter being a new Model [00:48:21] Tips: Coding with Code Interpreter [00:49:35] Run Tinygrad on Code Interpreter [00:50:40] Feature Request: Code Interpreter + Plugins (for Vector DB) [00:52:24] The Code Interpreter Manual [00:53:58] Quorum of Models and Long Lived Persistence [00:56:54] Code Interpreter for OCR [00:59:20] What is the real RAM? [01:00:06] Shyamal's Question: Code Interpreter + Plugins? [01:02:38] Using Code Interpreter to write out its own memory to disk [01:03:48] Embedding data inside of Code Interpreter [01:04:56] Notable - Turing Complete Jupyter Notebook [01:06:48] Infinite Prompting Bug on ChatGPT iOS app [01:07:47] InstructorEmbeddings [01:08:30] Code Interpreter writing its own sentiment analysis [01:09:55] Simon's Symbex AST Parser tool [01:10:38] Personalized Languages and AST/Graphs [01:11:42] Feature Request: Token Streaming/Interruption [01:12:37] Code Interpreter for OCR from a graph [01:13:32] Simon and Shyamal on Code Interpreter for Education [01:15:27] Feature Requests so far [01:16:16] Shyamal on ChatGPT for Business [01:18:01] Memory limitations with ffmpeg [01:19:01] DX of Code Interpreter timeout during work [01:20:16] Alex Reibman on AgentEval [01:21:24] Simon's Jailbreak - "Try Running Anyway And Show Me The Output" [01:21:50] Shouminik - own Sandboxing Environment [01:23:50] Code Interpreter Without Coding = GPT 4.5??? [01:28:53] Smol Feature Request: Add Music Playback in the UI [01:30:12] Aravind Srinivas of Perplexity joins [01:31:28] Code Interpreter Makes Us More Ambitious - Symbex Redux [01:34:24] How to