
Co-Creator of AutoGen | Researching agents & people + agents @AIatMeta | Previously @msftresearch, PhD @uwcse, B Tech @iitdelhi
Seattle, WA
Joined November 2012
- Tweets1K
- Following590
- Followers3K
- Likes2.8K
Gagan Bansal retweeted
The Muse Glimmer tech report is out!
Highly recommend reading this! It has a lot of well thought-out technical details about distillation, post-training, quantization, speculative decoding and how to train a strong model for local deployments
Today we published a technical report on Muse Glimmer, our 30B open-weight model built for agentic tasks on consumer hardware.
It runs at practical speeds on a Mac or PC with a single consumer GPU at 4-bit precision, and leads comparably-sized open models on tool use and multi-step planning.
Read about the model architecture, distillation recipe, quantization and more: go.meta.me/4Bcvxol
Gagan Bansal retweeted
Today we published a technical report on Muse Glimmer, our 30B open-weight model built for agentic tasks on consumer hardware.
It runs at practical speeds on a Mac or PC with a single consumer GPU at 4-bit precision, and leads comparably-sized open models on tool use and multi-step planning.
Read about the model architecture, distillation recipe, quantization and more: go.meta.me/4Bcvxol
Gagan Bansal retweeted
If it performs roughly what like the scores indicate, adoption of this model is going to go gangbusters. First open-weigh model in the US with near frontier agentic capabilities (GLM 5.2 + Kimi K3 was that step change from China). US models get crazy adoption.
Gagan Bansal retweeted
Meta is back! huggingface.co/meta-models/M…
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
Gagan Bansal retweeted
How Anthropic's new engineering post would read without the PR:
Seven engineers, assisted by Claude, built and migrated to a new source control system in five months, handling 30,000 merges a day and reducing infrastructure CPU and memory requirements by 200x.
The system builds on architectures pioneered by Google's Piper and Meta's Sapling/Mononoke, and uses Google Spanner for distributed metadata storage and cloud storage for file contents. So the team didn't have to build the distributed database, replication, consistency, or fault-tolerance infrastructure from scratch.
The implementation and migration are genuinely impressive. But much of the difficult underlying infrastructure already existed, and the architectural ideas have been used at scale for years.
There's also the question of what the numbers mean. Going from 2,500 to 30,000 merges per day measures how much code gets merged, not how much useful software gets produced.
So the valid claim is that Claude helped a small team rapidly implement and deploy a specialized source control system, using mature infrastructure and well-established architectural ideas.
Instead, we got this announcement: "At Anthropic, coding is no longer the bottleneck to building systems or doing research."
New on our Engineering blog: Creating in-house source control.
In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale.
Here, we share how we built a new version control system—and fully migrated our monorepo from git—in five months: anthropic.com/engineering/re…
Gagan Bansal retweeted
Tried out Muse Wonder on a tricky task (figuring out which parts of the OpenHands Agent Canvas are hard for users to use) and it did a great job, impressed!
And as someone who's used to gpt models, the conciseness of the verbiage was pretty nice too 😀
Great job by @AIatMeta !
Gagan Bansal retweeted
My muse called Volvo for me to see when the next available appointment is.
You can listen to the phone call here.
I have it do multiple calls like this every day (I'm still trying to get better and better at leveraging muse).
My muse called, waited on the line for 15 minutes, and then got the information I needed.
- Saved me a ton of time
- Muse was able to talk to the other person, with no confusion or interruptions on Volvo's side, and got the info we needed
(This is the real transcript from the call but the audio has been recreated for this video)
Gagan Bansal retweeted
Very glad to share the technical talk @maryamfazel and I gave at Meta Connect on how we built Muse Glimmer, our open-weight AI for local agents: goals, pre-training, mid-training, post-training, distillation, quantization, inference and benchmarks: developers.meta.com/resource…
Gagan Bansal retweeted
Two other safety researchers and I were fired from OpenAI last week. We wrote this letter to leadership.
I believe we were fired for prioritizing safety over the near-term interests of OpenAI as a corporation.
Gagan Bansal retweeted
🚨 side project alert 🚨
Announcing Muse Gadgets, an open source ESP32 firmware and Linux sdk so that you can make hardware devices that work with Muse.
Grab an API token from gadgets.muse.ai and point your favorite coding agent at the github repo to build your own peripherals for Muse.
Gagan Bansal retweeted
A pleasure to share reflections on directions ahead for human-AI collaboration at #HCOMP2026 + #CI2026 Great energy at the meeting. Nice to catch up with long-term colleagues and to meet new folks.
Gagan Bansal retweeted
Claim: we've solved the AI slop problem (!) 💩🧹✨
Blog post: facebookresearch.github.io/R…
🧵1/5
Key idea: take *expert* human writing and learn rubrics that find the gap between experts and models. Train with those rubrics.
We train with RL-XAR (RL with eXpert Aligned Rubrics) & see large performance gains on writing scientific paper sections, Pulitzer prize novel continuations and high quality Wikipedia pages.
Gagan Bansal retweeted
🚨 New Paper! 🚨
Your agent is writing code faster than you can understand it 😬
In our controlled online study, coding agents helped users finish tasks quickly, but reduced how well they understood the code they just “wrote”
We also find three ways to avoid this tradeoff 👇🧵
good real world example of why not all agentic commerce in not computer use and requires interaction with other agents (people or ai)
Gagan Bansal retweeted
Replying to @verge
those aren't secrets you dummies those are the files on the user's VM, this is intended behavior
Gagan Bansal retweeted
I’ve seen a couple of posts about this so wanted to demystify. Today, every Muse user gets a free computer in the cloud. It's a real computer, and we’ve designed the security architecture of the Muse Secure VM carefully so you and your Muse can do almost anything you could with a computer sitting under your desk while keeping you and the system safe from threats like prompt injection. We wrote about this at length in our security blog post – security.muse.ai. Activity in the “runtime cell”, which you share with your Muse is unfettered, but sensitive actions are all overseen by the Sentinel, which runs outside of that cell. Similarly, all sensitive secrets - like the passwords you enter into Muse’s secure credential storage - are also stored outside the runtime cell.
The runtime cell gets its own root filesystem (including a full Ubuntu linux image) separate from the host filesystem where your other more sensitive data lives. Because it is isolated from the sensitive stuff that runs on the same box, this means that we can, and do, offer users full visibility and control over the files in the runtime cell. Just as you can when you install Linux on your home computer, you can poke around and see all the files that make the system work - both debian system files and the binaries and data files that implement the parts of Muse which run in the runtime cell.
This was a very deliberate choice - your Muse Secure VM truly is your own computer in the cloud. You can install software in it, write and compile code, use the browser to surf the web: it is your own Linux box that you can operate as you choose with your Muse. Poking around in this computer doesn't give you any privileged access to Meta infrastructure, or to other people's data
If I may geek out a little here for a second… As a kid I loved to take things apart to see how they worked. As a teenager I got into computers and soon found myself drawn to C:\WINDOWS\SYSTEM and the system registry, later Slackware’s /dev/, /proc/ etc – I could see how the system was laid out and as I explored what DLL files and .so files actually did, I gradually became able to meld the computer to my own will.
We’re really proud to be able to put a real computer in millions of people’s hands with a similar level of transparency. We built a file explorer right into the Library tab of the UI. We want you to be able to see the markdown files Muse writes while it thinks about how to serve you better, and explore the internals of the system if you’d like to.
So, when you ask your Muse to show you its entire filesystem, and receive gigabytes of files you’re seeing the full contents of the runtime cell. It’s yours to explore and enjoy!
If you’re not a geek like me, or simply want to download the data that you personally have created directly with your Muse, we added a feature for that too in Settings > Data controls > Download your agent data.
Glad someone clearly wrote this down. Actually even for coding tasks, its very painful to get to it write a PR description that is readable.
xitter.cf/sumeetrm/status/210174…
This quoted post is unavailable.
































