Artificial IntelligenceSaturday, November 14, 20261 min read

Advancing science and engineering with Antigravity's /teamwork

By Hacker News · Published by Everything Blog

In short

The platform relies on Gemini 4 variants including Argon, Carbon, and Hydrogen to work alongside domain specialists via structured collaboration workflows. To ensure precision, tasks are isolated by assigning specialized agents targeted tools, while dedicated falsifiers such as Lean 4 and execution simulators validate findings. Notably, researchers from Google, CUHK, USC, and CMU utilized this system to successfully prove the 2013 Courtade–Kumar conjecture.

Key points

Google is providing external developers and researchers access to its /teamwork and /boos…: Google is providing external developers and researchers access to its /teamwork and /boost agentic toolsets.
Context dispersion over multi-day operations is minimized by partitioning workspaces and…: Context dispersion over multi-day operations is minimized by partitioning workspaces and assigning specialized agents only necessary files.
Independent critics and coordinators work with fresh successor agents to systematically r…: Independent critics and coordinators work with fresh successor agents to systematically review and progress long-horizon technical research.

Sources checked by our analysis pipeline: 1

November 13, 2026

Vahab Mirrokni, Google Fellow and VP, Google Research

We share recent results from Antigravity’s /teamwork multiagent systems, which enhance human-AI collaborations to solve open problems across mathematics, chemistry, systems software, and ML engineering. All of this work is done in collaboration with human experts, and we are making these tools available externally.

Over the past several weeks, teams across Google and academic partner institutions have tackled open problems in math, science, and complex systems engineering that had remained open for years. Using Gemini 4 Argon, Gemini 4 Carbon, Gemini 4 Hydrogen and multi-agent workflows such as Antigravity’s /teamwork (building on various Gemini models), these collaborations have produced new innovations across information theory, formal verifications, molecular structure discoveries, and kernel optimization, along with several production infrastructure gains at Google. We are making these agentic tools available in Antigravity’s /teamwork (alongside /boost and other agents) so that researchers and developers can apply them to their own work.

Frontier research and systems engineering require navigating vast literature, building custom computational pipelines, testing against physical measurements, and verifying every step. Progress…

AI Analysis

Tone

Positive

In short

Key Points

Google is providing external developers and researchers access to its /teamwork and /boos…: Google is providing external developers and researchers access to its /teamwork and /boost agentic toolsets.
Context dispersion over multi-day operations is minimized by partitioning workspaces and…: Context dispersion over multi-day operations is minimized by partitioning workspaces and assigning specialized agents only necessary files.
Independent critics and coordinators work with fresh successor agents to systematically r…: Independent critics and coordinators work with fresh successor agents to systematically review and progress long-horizon technical research.

Topics

Artificial Intelligence

Was this summary useful?

AI Analysis

Tone

Positive

In short

Key Points

Google is providing external developers and researchers access to its /teamwork and /boos…: Google is providing external developers and researchers access to its /teamwork and /boost agentic toolsets.
Context dispersion over multi-day operations is minimized by partitioning workspaces and…: Context dispersion over multi-day operations is minimized by partitioning workspaces and assigning specialized agents only necessary files.
Independent critics and coordinators work with fresh successor agents to systematically r…: Independent critics and coordinators work with fresh successor agents to systematically review and progress long-horizon technical research.

Topics

Artificial Intelligence

Was this summary useful?

The OpenAI board member who fired Sam Altman says we still can’t trust AI CEOs
Relying on individual executive integrity is an insufficient safeguard as advanced artificial intelligence systems rapidly evolve. Current governance models remain vulnerable to prioritizing commercial expansion over safety protocols, particularly following failed attempts to enforce internal corporate oversight. The continued use of voluntary accountability frameworks by federal authorities leaves broader national security and technological risks largely unmitigated.
65 min read
The Claude Delusion
Highly successful technology figures frequently presume their specialized programming skills grant them universal mastery across unrelated disciplines. Former Microsoft executive Bill Gates recently demonstrated this mindset by using his personal abilities and custom tests to measure artificial intelligence capabilities. This dynamic illustrates how industry leaders often treat their own proficiencies as the absolute benchmark for broader human achievement.
7 min read
A visual explanation of reinforcement learning
Digital creatures called sparks can autonomously master complex navigation using minimal neural architecture paired with automated trial and error. By applying rewards and penalties to incremental wiring changes, algorithms guide these simple organisms to self-correct and achieve goal-oriented navigation. Visual mapping shows that disparate, randomized starting states routinely converge into identical functional brains over thousands of training runs.
7 min read

Advancing science and engineering with Antigravity's /teamwork

In short

Key points

More in Artificial Intelligence