A developer's red-teaming exercise demonstrates that AI agents remain vulnerable to prompt injection attacks, using a spreadsheet-based task to show how hidden instructions in Excel files can manipula…
Software developer Simon Willison describes his deliberately simple workflow with Anthropic's Claude Code, using only a CLAUDE.md file of rules instead of skills, MCP, or subagents. His rules include …
Simon Willison added D2 diagram support to his static site generator, allowing him to compile D2 files into SVG diagrams for blog posts. The feature, implemented via a Python function that invokes the…
Software engineer Niklas Gruhn coined the term 'meat proxy' in an August 3 blog post to describe coworkers who blindly copy-paste AI chatbot output without review, a practice he says adds no value. Th…
A new term, 'meat proxy,' emerged in 2026 to describe a person who forwards AI-generated text or code without reading or validating it, with the earliest use found in an anonymous March 31, 2026 blog …
A new pejorative term, 'meat proxy,' coined by developer Niklas Gruhn and popularized by Simon Willison, describes people who forward AI-generated responses without reading or verifying them. The term…
Anthropic's most advanced AI model, Fable 5, accounts for only 11% of enterprise spending on the company's tools, according to data from fintech firm Ramp. Enterprises are opting for cheaper models li…
A developer reflects on the importance of delivering proven, working code rather than merely generating large patches with AI assistance. The post emphasizes that agent-generated code is cheap and tha…
Simon Willison released llm-anthropic 0.27, an Anthropic plugin for LLM, to ensure compatibility with the anthropic v1.0.0 Python library, which switched from httpx to httpx2. The update was prompted …
Alibaba's Qwen 3.8 27B open-weight vision model, released under Apache 2.0, takes 21 minutes and 22,276 reasoning tokens to draw a pelican riding a bicycle as an SVG, according to Simon Willison's tes…
Invariant Labs researchers demonstrated in April 2025 that a malicious Model Context Protocol server could silently exfiltrate a user's entire WhatsApp message history by hijacking a tool description,…
Simon Willison, a software engineer and blogger, launched Agentic Engineering Patterns, a new project documenting coding practices for building software with coding agents such as Claude Code and Open…
Simon Willison released LLM 0.33 on August 22, 2026, as a non-prerelease version, moving the project's HTTP dependency from httpx to httpx2. The update follows a temporary compatibility fix in LLM 0.3…
Simon Willison released llm 0.33, a command-line tool for running LLMs, which adds a --key option to llm embed and llm embed-multi commands and corresponding Python methods, allowing per-call keys for…
Simon Willison argues that the key skill for using coding agents is confidently instructing them and verifying changes, noting that reviewing every line of code is not the most effective validation me…
Qwen 3.8, a 27B-parameter open-weights model from Alibaba, delivers coding output in the Claude Haiku-to-Sonnet range but is 15-20 times slower than Claude Sonnet, according to tests by a developer on…
Simon Willison released LLM 0.32.1 on Aug. 21, pinning the OpenAI Python dependency below version 3.0.0 to ensure fresh installations work without a separate httpx install. The maintenance update addr…
Simon Willison released llm-openrouter 0.7 on Aug. 21, updating the plugin for compatibility with LLM 0.32 and switching to OpenRouter's implementation of the Responses API. The release adds Shell, We…
A 30-month study of 26,811 Chinese high school students found that AI tools boosted homework scores by 18% and cut homework time by 30%, but monthly exam scores dropped 20% within six months and colle…
Simon Willison, a software developer, reports that he continues to use two macOS task bar apps he built with vibe-coded SwiftUI in March, and he endorses Thomas Ptacek's advice that developers should …