OpenAI Codex Gets Computer Use, Browsing, and Memory
OpenAI’s updated Codex app for macOS and Windows adds computer use, in-app browsing, image generation, memory, and plugins. Here’s what that means for developers.
OpenAI’s updated Codex app for macOS and Windows adds computer use, in-app browsing, image generation, memory, and plugins. Here’s what that means for developers.
Google now offers prepay billing for the Gemini API in AI Studio. Here’s what it means for developers managing costs and scaling AI projects in 2026.
OpenAI’s Agents SDK update adds native sandbox execution and a model-native harness. Here’s what that means for developers building long-running AI agents.
Google Colab’s new Learn Mode uses Gemini AI to teach coding step-by-step instead of just writing code for you. Here’s what changed and why it matters.
OpenAI’s Codex now offers pay-as-you-go pricing for ChatGPT Business and Enterprise teams. Here’s what changed, what it costs, and why it matters.
Google’s new Flex and Priority inference tiers let developers trade latency for cost savings in the Gemini API. Here’s what that means for your build.
Google’s Veo 3.1 Lite is now in paid preview via the Gemini API. Here’s what it costs, what it can do, and who should actually care.
Google launched Gemini API Docs MCP and Agent Skills to stop coding agents from writing outdated Gemini API code. Here’s what developers need to know.
Google’s Gemini 3.1 Flash Live is now in Google AI Studio via the Live API — here’s what developers need to know about building real-time voice and vision agents.
OpenAI releases prompt-based teen safety policies via gpt-oss-safeguard, giving developers a practical way to moderate age-specific risks in AI apps.
OpenAI is acquiring Astral, the team behind Ruff and uv, to accelerate Codex and build the next generation of Python developer tools. Here’s what it means.
Google’s Gemini API now supports combining function calling with built-in tools like Search in a single call. Here’s what that means for developers building agents.