Simon Willison — Independent developer and writer documenting practical experiments, tools, and deep analysis around large language models, generative AI, web development, security, and emerging programming workflows through detailed posts and daily TILs.
117 articles from this blog
Explains the technical design of Fly.io's Sprites, focusing on fast provisioning via warm pools and a custom persistence layer using JuiceFS and SQLite.
OpenAI researchers propose 'confessions' as a method to improve AI honesty by training models to self-report misbehavior in reinforcement learning.
A security vulnerability in Claude Cowork allowed file exfiltration via the Anthropic API, bypassing default HTTP restrictions.
Anthropic invests $1.5 million in the Python Software Foundation to support Python ecosystem security and core development.
A prompt injection attack on Superhuman AI exposed sensitive emails, highlighting a critical security vulnerability in AI email assistants.
A hands-on review of Anthropic's new Claude Cowork agent, exploring its interface, capabilities, and potential as a general AI assistant for non-developers.
Argues against anti-AI sentiment in software development, stating AI is a permanent, useful tool that will democratize coding and improve productivity.
Author explores the legal and ethical implications of using LLMs to port open source code between programming languages, based on personal experiments.
A blog post quoting Linus Torvalds on using AI-assisted 'vibe-coding' to create a Python audio visualizer tool.
An experiment in creating a software library with no code, using AI agents to generate implementations from specifications and tests.
Fly.io launches Sprites.dev, a stateful sandbox environment for secure coding agents and untrusted code execution.
A tech expert shares predictions for 2026 on a podcast, focusing on the future of LLMs, coding agents, and AI-assisted software development.
Analysis of Google's AI comeback, including the origin of 'Nano Banana', Sergey Brin's return, and Gemini's user growth compared to OpenAI.
Tailwind Labs CEO discusses the severe business impact of AI, including layoffs and revenue decline, despite the framework's growing popularity.
A reflection on the arrival of Artificial General Intelligence (AGI), arguing that its 'general' nature distinguishes it from previous purpose-built AI models.
A comprehensive guide to different sandboxing technologies for safely running untrusted AI code, covering containers, microVMs, gVisor, and WebAssembly.
A critique of the new, overly complex menu icons in macOS Tahoe, arguing they violate design principles and fail to aid usability.
