tldraw issue: Move tests to closed source repo
Simon Willison discusses a concerning trend where comprehensive test suites of open-source libraries can be detailed enough to allow a complete re-imp...
Simon Willison
You don’t know what your agent will do until it’s in production
LangChain highlights the unique challenges of monitoring AI agents in production, emphasizing their non-deterministic nature and the importance of con...
LangChain
Google API Keys Weren’t Secrets. But then Gemini Changed the Rules.
Simon Willison reports a significant security concern regarding Google API keys, noting that Gemini and Google Maps share the same keys. This poses a ...
Simon Willison
ByteDance’s Seedance 2.0 Shows Promise in Generative AI Video, Still Imperfect
ByteDance's latest video generation model, Seedance 2.0, is demonstrating significant progress in generative AI video, as showcased by filmmaker Ruair...
The Verge AI
AI Chip Startup MatX Raises $500M to Challenge Nvidia
MatX, an AI chip startup founded by former Google TPU engineers in 2023, has secured a substantial $500 million in funding. This significant investmen...
TechCrunch AI
GPT 5.3 Codex Now Available on AI Gateway
Vercel's AI Gateway now features GPT 5.3 Codex, a new model that integrates the strong coding capabilities of GPT-5.2-Codex with the advanced reasonin...
Vercel
Establishing Security Boundaries in Agentic Architectures
Vercel emphasizes the critical need for robust security boundaries within agentic architectures, as current agents often execute generated code with e...
Vercel
Vercel Increases Python Functions Bundle Size Limit to 500MB
Vercel has announced an increase in the bundle size limit for Python Vercel Functions, raising it from 250MB to 500MB. This enhancement provides devel...
Vercel
Introducing go-size-analyzer for Go Binary Analysis
A new tool named `go-size-analyzer` has been highlighted for its robust capabilities in analyzing the size of Go binaries. It offers a clear treemap v...
Simon Willison
Engineering Reliable Multi-Agent Workflows
The GitHub Blog addresses the common failures in multi-agent workflows, attributing them primarily to a lack of structural design rather than inherent...
GitHub Blog
Exploring Linear Walkthroughs in Agentic Engineering Patterns
Simon Willison discusses 'linear walkthroughs' as an effective agentic engineering pattern. This method leverages coding agents to provide structured ...
Simon Willison
Exploring AI’s Challenges in Reading Complex PDFs
This piece explores the challenges and potential failures of AI in processing and understanding complex documents like PDFs, particularly in the conte...
The Verge AI