How Project HydraFusion reduces the cost of frontier AI

Aashna Garg and Julia Kasper explain Project HydraFusion in GitHub Copilot, focusing on how orchestrating multiple models per request (instead of selecting a single model) can reduce frontier-model costs, and how the approach is evaluated with demos and benchmarking.

Overview

The video introduces Project HydraFusion, a GitHub Copilot approach that aims to reduce the cost of using frontier AI models by orchestrating existing models per request rather than always choosing a single model.

What HydraFusion is trying to solve

Where HydraFusion shows up

Why “model routing” alone isn’t enough

The three workflows (as described in the video chapters)

Cascade workflow

Critic workflow

Side-by-side cost comparison

Reported savings and evaluation

Resources

Video chapters