AI
Building Long-Running AI Agents That Actually Survive: A Practical Look at Google's ADK
Most agent tutorials build stateless chatbots that forget everything when the container restarts. Google's Agent Development Kit takes a different...
AI
Articles about AI, agents, language models, tooling, and practical experiments using artificial intelligence.
AI
GPT-5.5 First Impressions: What OpenAI's Latest Model Means for Developers
OpenAI just shipped GPT-5.5 with big claims about agentic coding, efficiency, and real-world autonomy. I haven't tried it yet—but here's what the...
AI
OpenAI Codex Expanded: A Developer's Guide to the New AI Pair Programmer
OpenAI just released a major Codex update with computer use, in-app browser, image generation, 90+ new plugins, and memory. Here's what developers...
AI
Gemini 3.1 Flash TTS: A Practical Guide to Building Dynamic Voice Interfaces
Google's new text-to-speech model introduces promptable audio tags for granular control. Here's how to use them in real projects—from audiobooks to...
AI
Claude Opus 4.7: What's New and Why Developers Should Care
Anthropic's latest flagship model brings meaningful improvements in coding autonomy, vision, and safety. Here's what changed between 4.6 and 4.7—and...
ai
How SafeRide Health Adopted AI in Engineering: Velocity Gains, Budget Lessons, and a Veteran Engineer's Perspective
After adopting Cursor across our engineering team at SafeRide Health, we saw major velocity improvements—but also burned through a third of our...
ai
Anthropic’s Mythos Moment Feels Familiar, and Not in a Good Way
Anthropic’s Project Glasswing and Mythos Preview may point to real advances in AI-assisted security work, but for developers and tool builders the...
ai
Running This Blog With an AI Team, While Keeping It Human
josephcrawford.com is now being run by Joseph alongside a small AI team focused on writing, research, engineering, and operations, with Joseph still...