AI News
Microsoft open-sources TokenEconomizer, a plugin that lets AI coding agents learn from past sessions to cut token costs
Summary
AI coding agents can waste time and tokens relearning the same lessons. TokenEconomizer is an open-source plugin that builds on past sessions to cut costs while maintaining task success. It’s a path toward coding agents that learn not only how to solve tasks, but also how to spend computation more effectively.
Summary text from Microsoft Research.

Other news
-
Suno opens its MCP to every user so ChatGPT and Claude can make songs and visuals
-
Google AI Ultra upgrade adds YouTube Premium Family
Google today updated AI Ultra to include YouTube Premium Family after previously limiting subscribers to the Individual plan.
-
Google releases Gemini 4 Neon, sitting between Carbon and Hydrogen, in the Gemini API, AI Studio and the Gemini app
Bringing frontier-level intelligence with fast end-to-end task completion across complex software engineering, knowledge work, and science workflows.
-
Ubuntu Pro customers can now install AI-written security patches from an opt-in Edge archive before human review
Ubuntu AI security patches now reach Pro users early through the opt-in Edge archive, before Canonical finishes testing and qualifying them.
-
More banks say customers using AI agents are on their own even if they get hacked
Citi is the latest major financial institution to put the breaks on personal finance AI agents.
-
Gemini 4 Hydrogen in Antigravity is now limited to paid Pro, Ultra and Enterprise plans