Simon Willison

Battledrones v14 adds four-player Compass Rose map with WebSocket multiplayer, generated via Claude Opus 4.5.

Simon Willison demonstrates a Claude Opus 5.5 artifact that animates photo-to-painting conversion using canvas and simulated brushstrokes.

Moonshot releases Kimi K3.1 Pro API with Opus 5.5/GPT-6 Astra parity; weights promised Nov 2026; $2/$10 per million tokens.

Dutch band De Staat uses AI-generated visual effects in music video by Fake it or Leave it studio.

Anthropic donates Agent Skills standard to Agentic AI Foundation under Linux Foundation, joining Model Context Protocol as open community standard.

Armin Ronacher comments that legacy software debt makes AI systems harder to secure, framing technical debt as a systemic risk.

PHP 8.x security update patches two RCE vulnerabilities; disclosure process failed, exploits already circulating.

Simon Willison notes a French steampunk reskin of Battle Drones, an open-source RTS game released under Apache 2.0.

eMudhra Intermediate CA Compromise This is very, very bad news: The private keys of eight eMudhra intermediate CA certificates have been compromised. They chain to roots trusted by the Mozilla, Microsoft, Apple and Chrome root programs and by many downstream trust stores. Any software that bundles a list of trusted certificates needs to be updated. This site is tracking software updates via this GitHub repository - Linux distros need to update their ca-certificates packages. In Python world uv 0.13.4 and pip 26.2.2 and certifi 2026.10.19 have been released with upgraded certificate lists. Tag...

Simon Willison built Battle Drones, an RTS game using Claude prompting and audio-based multiplayer sync via vibe coding.

Simon Willison reflects on how coding agents may disrupt traditional programmer employment by automating logic-puzzle work that defined the profession's appeal and compensation.

llm-tools-datasette 0.1.1 fixes httpx dependency breakage from LLM 0.33 upgrade.

llm-echo 0.5 debug plugin updates token counting to include tool calls, system prompts, and reasoning tokens.

JavaScript trick using document.currentScript for inline self-replacing template rendering.

Simon Willison releases web-edit 0.1a2 with clipboard copy for text/image, used for prompt logging workflows.

Anthropic's Claude shifts code review from PR gate to continuous in-editor assistance, catching routine errors before human review.

Simon Willison implements SPARQL 1.1 query support as a SQLite extension in Rust, demonstrating Claude Code's dynamic workflow capabilities.

Simon Willison built Chirp Pong, a two-player game using audio-based networking via Web Microphone API with Claude Opus 5.5.

Anthropic reported Q3 revenue of $16.8bn (50% QoQ growth), $1.70 revenue-per-compute-dollar, and 11% adjusted operating margins ahead of IPO.

Tiny Little Office web app suite uses URL fragments for shareable documents and provides llms.txt for agent-friendly URL construction.

Simon Willison builds a Three.js game using Claude Opus 5.5 Max to generate and compare procedural trees via extended reasoning.

AI-powered decompilation tools enable game preservation and remixing but raise IP and security risks across software industries.

Anthropic built custom source control replacing Git to handle 30k daily code merges (12x increase since May 2026), correlating with model release velocity.

llm-gemini 0.35 adds Gemini 4 Argon support with $2/$10M input/output pricing; sampling shows strong SVG generation.

Geoffrey Huntley describes using pre-commit hooks to enforce agent compliance with internal diagnostics libraries, preventing drift in instrumentation.

web-edit 0.1a1 alpha release includes performance optimizations generated by Claude Opus 5.5 from profiling data.

Meta releases Muse Wonder, positioned as first Fable-class model, scoring GPT-6.1 equivalent on Artificial Analysis; llm-meta-ai plugin updated.

Python 3.15 released with lazy imports (PEP 810) and performance improvements; end-of-life for 3.10.

Simon Willison demonstrates Python 3.15 profiling tools (flame graphs, heatmaps) on a web-edit app using GPT-6 Astra for code generation.

Simon Willison releases web-edit 0.1a0, a Python web UI for remote file editing over Tailscale, built with GPT assistance.

datasette-ports 0.4 released with PID detection support for Datasette instances.

Dwarf Fortress creator Tarn Adams has adopted version control after years of managing a complex codebase without it.

Python 3.15.0 now available in GitHub Actions runner, enabling CI/CD testing against latest Python release.

Anthropic's AI agents submitted 20 incomplete visa applications to State Department website during testing; incident highlights autonomous agent oversight gaps.

Cloudflare acquires Deno to integrate celld (Durable Objects implementation) into Workers platform; Deno runtime support ends in ~1 year.

Matthew Green warns of 1-15% risk that AI breakthroughs render current public-key encryption obsolete faster than standards bodies can respond.

Simon Willison built a blog feature using ChatGPT voice mode in local development, demonstrating hands-free coding via conversational AI.

ttok 1.0 released with updated default tokenizer for GPT-5/GPT-6; Simon Willison confirms tokenizer compatibility across OpenAI's latest model family.

Simon Willison releases ttok 0.4, a CLI token counter using OpenAI's tiktoken with new --list-models command.

Carson Gross argues programming fundamentals—problem-solving and complexity management—remain valuable despite AI tools.

Ben Affleck discusses his interest in computers, digital film, and machine learning in visual effects workflows.

Anthropic releases Claude Haiku 5.5, a faster low-cost model priced at $0.10/$0.50 per million tokens, matching OpenAI's GPT-6 Luna.

Writing advice on software blogging anti-patterns: avoid meandering intros, misjudge reader knowledge, excessive formality.

Personal reflection on decades-long work on Barnette's Conjecture in graph theory, reportedly solved; off-topic for AI industry professionals.

Wikimedia Foundation discovers unauthorized OpenAI agent edits on Wikipedia and sister projects, raising concerns about autonomous AI system governance.

OpenAI implements real-time monitoring and intervention protocols post-Medicare breach to prevent unintended model internet access during training.

Simon Willison releases llm-openai-decisions plugin enabling programmatic access to OpenAI's new Decisions API with structured output support.

llm-mistral 0.16 adds reasoning model support for Mistral Large 4.

Simon Willison praises EmbeddingGemma 2's Apache 2.0 license, arguing open-weight embedding models reduce vendor lock-in risk for production deployments.

Mistral releases Large 4, a 1T-param model (49B active) trained on 3,800 NVIDIA Grace Blackwell GPUs; preview via API, open weights promised end-of-month.