Tooling10d ago
Microsoft Research and UC Berkeley open-source TokenEconomizer, a plugin that cuts Claude Code and Codex costs by 18.4–30.9% on SWE-Bench without changing the agent
Microsoft Research, Microsoft Security and UC Berkeley open-sourced TokenEconomizer on GitHub (Apache 2.0, v0.1.0 released October 26), a plugin for Claude Code, Codex, GitHub Copilot CLI and Pi, with experimental opencode support. It learns from earlier sessions in the same repository: micro-skills remember repo facts, tool pruning drops tool definitions that go unused, and a loop guard nudges an agent that is stuck. The paper reports 18.4–30.9% lower mean cost across five agent and model combinations on 277 SWE-Bench tasks (paper figures).
Tooling52d ago
Gemini API lists antigravity-preview-09-2026: Antigravity agent endpoint, not a new model
The Gemini API now lists id antigravity-preview-09-2026. It is not a new Pro/Flash model but the Antigravity managed-agent endpoint: Linux sandbox with code execution, files, and browser, defaulting to Gemini 3.8 Flash. Google-affiliated Philipp Schmid confirmed it is the Gemini API agent harness, with more details expected later this week.
Release15d ago
OpenAI frontier models and Codex are coming to Google Cloud: Model Garden access, bought via Marketplace against existing GCP commitments
On Oct 21, OpenAI and Google Cloud announced a partnership bringing OpenAI frontier models and Codex agentic workflows into Google Cloud Model Garden, transacted through Google Cloud Marketplace so enterprises can draw down existing GCP commitments. OpenAI models will also come to Google Antigravity and Gemini Agent soon. General availability is planned in the coming weeks, and Microsoft remains OpenAI's primary cloud partner. After AWS, this puts OpenAI models on all three major US clouds.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.