OpenAI GPT-Realtime-2: The Voice API That Can Reason
OpenAI's gpt-realtime-2 adds configurable reasoning to speech-to-speech APIs. The beta is gone. Here is what changed, what to migrate, and why it matters.
AWS Kiro Requirements Analysis: Formal Verification for AI Coding Agents
AWS Kiro shipped Requirements Analysis, using an SMT solver to find bugs in 60% of ...
Google I/O 2026: The Developer Signals Worth Watching
Google I/O 2026 starts May 19. Jules is Google's async coding agent, ADK 1.0 ships ...
Vercel Deepsec: AI Agents Scan Your Code for Flaws
Vercel open-sourced deepsec, an AI security scanner using Claude Opus 4.7 and GPT-5.5 to find ...
Rolldown 1.0 Is Stable: What Vite Developers Need to Know
Rolldown 1.0 is now stable — the Rust bundler powering Vite 8. Here’s what the ...
Gemini 2.5 Flash Preview 05-20: What Developers Get
Google's gemini-2.5-flash-preview-05-20 ranks #2 on LMarena. Here's what thinking budget controls, the URL context tool, and thought summaries mean for your stack.
Atlassian Teamwork Graph: CLI and MCP Server Now Open
Atlassian opened its 150-billion-object Teamwork Graph to AI agents at Team 26. Here is what ...
Firebase AI Logic Is Now GA: What Developers Get at Google I/O 2026
Firebase AI Logic is now generally available at Google I/O 2026. Here's how the Gemini ...
Claude Advisor Tool: Opus Intelligence at Sonnet Cost
Anthropic's advisor tool lets you run Sonnet with Opus as a strategic advisor in a ...
Tailwind CSS Layoffs: How AI Broke the OSS Business
Tailwind CSS hits 75M downloads/month but cut 75% of engineers after AI killed doc traffic ...