OpenAI now gives eligible $100, $200 and $500 ChatGPT subscribers the same dollar amount in credits for an API organization. It mirrors a benefit Anthropic announced earlier this month for its Max and Team plans. For developers who pay for both a coding assistant subscription and API usage, it changes the cost math.
Simon Willison highlights Jacob Sansbury's account of building Spawn, a multiplayer game world changed by prompts to an in-game AI. The team says a swarm of Fable-powered agents edits live code and ships to production about hourly. It is a rare, concrete look at how far coding agents can run autonomously in production.
Amp can now boot a cloud Mac during a thread to build, test and run iOS and macOS apps. The feature, macOS Satellites, is in beta and billed hourly. For developers working on Apple platforms, it changes how an agent verifies its own changes.
The new GitHub security extension for the GitHub Copilot app lets you browse code scanning alerts, ask Copilot to explain or fix them, and run a security review on local changes without leaving the app. It is in public preview. Developers who already rely on code scanning will find it a faster way to handle alerts.
GitHub introduced GitHub intelligence, a context layer for Copilot agents. Copilot Memory is now generally available on paid plans, dreaming is in public preview, and Copilot can search code across repositories without a local clone. Agents can now keep your preferences and team conventions between sessions and reach related projects.
GitHub is rolling out shared Copilot Automations, so a repository's cloud agent workflows no longer depend on the person who created them. Teams can read, edit and keep running these automations, with AI credits billed to the repository owner. Useful for bug reproduction, PR screenshots and incident triage.
GitHub has expanded how Copilot agents run in VS Code. Cloud sessions can be picked up across VS Code, GitHub Mobile and github.com, while the new Agent Host keeps local and remote agents running after you close a window. Computer use and side-by-side model comparison arrive as preview or experimental features.