GitHub's HydraFusion hits VS Code and Copilot app: multi-model routing at lower credit cost
DanWahlin · x · 2026-10-01
GitHub officially expanded the HydraFusion research preview from Copilot CLI to VS Code and the GitHub Copilot app.
It's not a single model but treats workflow selection as an optimization problem: using capability signals for reasoning, code generation, debugging, and tool use, it picks the most efficient execution pattern across three workflows:
- Single: one model solves the task directly
- Cascade: an efficient model drafts, a quality gate decides whether to escalate to a stronger model
- Critique: one model drafts, an independent read-only critic from a different model family reviews, and the drafter revises once
GitHub's kdaigle says it delivers performance similar to Fable/Astra at much lower AI credit cost. Requires VS Code 1.140+, enable via the model picker (or chat.copilot.hydraFusion.enabled); org/enterprise accounts need an admin to allow preview features.
More from coding & agent
- New tool makes benchmarking across factory configs trivial, not just models — vikvang1 · 2026-10-01
- Magnitude inference engine hits #1 on HN, claims up to 2x faster local open-model runs than llama.cpp — nickbaumann_ · 2026-10-01
- marimo-lens lets you point at charts and steer your coding agent directly — S_Conradi · 2026-10-01
- Non-coder builds MCP-only medieval trade game played entirely by AI agents — Wainfare · 2026-10-01
- Dev roasts Claude Code's Opus for forgetting UI parameters, makes No Country meme — firasd · 2026-10-01
- Solo fine-tune of Qwen3.8-27B-pi fixes effort ordering, saves 41% tokens — victormustar · 2026-10-01