Aashna Garg retweeted
We got a LOT of questions about how the new Copilot Fusion works under the hood.
@aashna and friends walk us through the science and engineering details that lead to this breakthrough:
youtu.be/1kpeIbdAfoQ?si=p6Wq…
"Just today, GitHub Copilot Fusion was ranked as the #1 coding agent on Terminal Bench scoring 5 points over Claude Code at less than half the cost."
tbench.ai
🆕 On Terminal-Bench 4.1, Copilot Fusion Max achieved a 71.2% resolution rate, 5.4 percentage points ahead of leading frontier models Opus 5.5 and Fable 5.2, while costing 88% less than Fable 5.2 and 57% less than Opus 5.5.
docs.github.com/copilot/conc…
Aashna Garg retweeted
1/6 💡 How can advanced AI become more useful, trustworthy and affordable?
In our interview, Aashna Garg, Principal Applied Scientist at Microsoft working on GitHub Copilot, connects applied research, production engineering and evaluation. #ArtificialIntelligence

ALT Interview graphic featuring Aashna Garg on the left and Stephen Ibaraki on the right. Aashna is a Principal Applied Scientist at Microsoft working on GitHub Copilot. Theme: making powerful AI more useful and affordable through how models work together. Three practical ideas: 1. Route: match the model to the task. 2. Orchestrate: design how models collaborate. 3. Evaluate: test quality, latency and cost together. Question: What could your team solve with a better AI workflow?
Aashna Garg retweeted
GitHub Copilot Fusion mixes models to achieve near-Opus 5.5 coding performance at half the per-task cost
venturebeat.com/ai/github-co…
Aashna Garg retweeted
We're redefining the SDLC for the agentic era.
Lots of GitHub updates this morning at Universe:
• GitHub Copilot Fusion delivers frontier-level quality, 40% faster and at up to 77% lower cost
• Our unified Copilot harness is now in Foundry, a managed service for building long-running agents that reason, use tools, and get work done
• Copilot Projects gives you an orchestration loop to build with multiple agents across repos
And we’re expanding capacity and strengthening GitHub’s architecture to make the home of agentic development more resilient.
👋 Project HydraFusion is now available in the GitHub Copilot app and @code.
Choose it like any other model. Behind the scenes it routes your task across multiple models to draft, critique, revise, or escalate, then hands you one result. github.blog/changelog/2026-0…
Aashna Garg retweeted
Project HydraFusion in GitHub Copilot achieves frontier-level quality at up to 67% lower cost!
It achieves this via runtime orchestration that creates a plan, chooses models from multiple providers to draft, critiques and revises, or cascades to more powerful models to complete your task.
github.blog/ai-and-ml/github…
Aashna Garg retweeted
HydraFusion in Copilot CLI isn’t another model in the picker. You select it once. It decides whether the task is a single pass, a cheap draft with a quality gate, or draft → critique → revise.
Wrote it up in plain English
Aashna Garg retweeted
GitHub quietly dropped one of the most interesting infrastructure ideas I've seen this year. They're calling it HydraFusion.
The concept: instead of picking one frontier model, the system routes tasks through a combination of models using three execution patterns. Single routes to one model. Cascade tries a cheaper model first, escalates if it fails. Critique uses one model to generate and a second to review. The system picks the pattern based on the task.
The results from their research preview are the interesting part. On TerminalBench 2.1, HydraFusion gets within 4.9 points of Claude Opus 5 quality at 67% lower cost. On DeepSWE it's within 1.5 points at 36% lower cost. On CheckpointBench, within 0.1 points at 65% lower cost.
Those numbers matter more than the headline. Getting within 0.1 points of a frontier model at one-third the cost is not a marginal improvement. That's a different category of trade-off.
Access is live now. Type /experimental in GitHub Copilot CLI, then /model to select HydraFusion (Research Preview). Available on all plans.
What I keep coming back to: model orchestration is becoming its own engineering discipline. The question isn't which model to use anymore. It's how to compose them. GitHub putting this into the CLI layer is the right place to start.
teapawt.org/github/status/20959071…
4.9 percentage points higher verified task quality. 67% lower estimated cost.
Project HydraFusion delivered those results against Claude Opus 5 on Terminal-Bench 2.1 in controlled offline evaluations.
HydraFusion orchestrates the models and workflow for each coding task. You select it like any other model. ⬇️
github.blog/ai-and-ml/github…
4.9 percentage points higher verified task quality. 67% lower estimated cost.
Project HydraFusion delivered those results against Claude Opus 5 on Terminal-Bench 2.1 in controlled offline evaluations.
HydraFusion orchestrates the models and workflow for each coding task. You select it like any other model. ⬇️
github.blog/ai-and-ml/github…
Aashna Garg retweeted
Same or better quality, much lower cost, no manual model orchestration. That's what we're delivering Project HydraFusion from GitHub.
Early tests have been very positive and we're improving hourly. Give it a try and let us know what you think. 👇 github.blog/ai-and-ml/github…
Aashna Garg retweeted
Super excited about HydraFusion in GitHub Copilot, and what it shows about the shift from model selection to model orchestration.
By bringing together multiple models to plan, build, critique, and complete coding tasks, it can deliver outcomes at up to 67% lower cost.
It’s a great example of the value of a heterogeneous model ecosystem, and how we’re continuing to advance the cost-to-outcome frontier.
Aashna Garg retweeted
Excited to share HydraFusion, our latest research preview in GitHub Copilot CLI. HydraFusion delivers frontier intelligence through adaptive multi-model orchestration. It dynamically combines models and orchestration patterns to balance quality, cost, and latency.
4.9 percentage points higher verified task quality. 67% lower estimated cost.
Project HydraFusion delivered those results against Claude Opus 5 on Terminal-Bench 2.1 in controlled offline evaluations.
HydraFusion orchestrates the models and workflow for each coding task. You select it like any other model. ⬇️
github.blog/ai-and-ml/github…
Aashna Garg retweeted
Today, we announced the Abnormal Integrated Cloud Email Security (ICES) platform, the only cloud-native solution for comprehensively and precisely stopping all email threats.
Learn more in the Abnormal Blog: https://teapawt.org/t.co/oyUIVl0z47
Aashna Garg retweeted
A couple papers from 2016.
Sort of like those doomsday movies with the ignored scientist warning of impending doom.
Aashna Garg retweeted
Microsoft researchers and engineers release Zero Redundancy Optimizer (ZeRO) and DeepSpeed library, a system able to train 100-billion-parameter deep learning models. Learn about this breakthrough and how it led to Turing Natural Language Generation: aka.ms/AA79s5c
Aashna Garg retweeted
Announcing PyTorch Hub!
Want ResNet, ResNext, BERT, GPT, PGAN, Tacotron, DenseNet, MobileNet...?
- Pull models with 1 line of code.
- Publish your models by sending a pull request.
More info here:... pytorch.org/blog/towards-rep…
Aashna Garg retweeted
The AI Index is out! Page after page of interesting charts showing AI trends. aiindex.org/ For example, since 2013, the share of US jobs requiring AI skills has grown 4.5x! @yshoham


























