Google's Antigravity Teamwork + Gemini 3.7 Flash Solves 7 Open Math Problems
rseroter · x · 2026-09-01
A Google blog post details Teamwork, the multi-agent orchestration framework in Antigravity: agents autonomously propose, critique, and refine each other's work over hours or days. Paired with the newly launched Gemini 3.7 Flash, it was used to solve 7 open problems in mathematics and theoretical CS, including sparse convex optimization (JMLR) and subspace approximation (FOCS).
Gemini 3.7 Flash balances speed and cost for everyday tasks; combined with Teamwork's frontier orchestration, it performs strongly on long-horizon, open-ended research and software engineering problems. Available via /teamwork-preview.
More from coding & agent
- Anthropic borrows lawyers' ethics for Claude agents that closed 186 deals with no human approval — rohanpaul_ai · 2026-10-18
- Prompt injection via email can hijack your AI agent — jev-guard adds risk-scored guards — sujingshen · 2026-10-18
- 14-Agent AI Film Pipeline on One RTX 5090: Fixing Cut Defects Between Clips — developervkmp · 2026-10-18
- Meta paper introduces "agent plasticity": best-performing agent isn't the most efficient learner — rohanpaul_ai · 2026-10-18
- Dev ships a bushfire prediction platform in a weekend with frontier models — CtrlAltDwayne · 2026-10-18
- 10 open-source GitHub repos that let AI agents control your phone, from Open-AutoGLM to mobile-use — victor_explore · 2026-10-18