Co-Creator of AutoGen | RS @ Meta Superintelligence Labs | Previously @msftresearch, PhD @uwcse, B Tech @iitdelhi
Seattle, WA
Joined November 2012
- Tweets1.1K
- Following591
- Followers3K
- Likes2.8K
Gagan Bansal retweeted
We mourn the passing of Patrick Stewart, who inspired countless individuals at NASA (and beyond) to boldly go where no one has gone before.
ALT Image description: A packed, sparkling starfield captured by our Hubble telescope — with strange new worlds potentially awaiting. Credit: ESA/Hubble and NASA, R. Cohen
Gagan Bansal retweeted
Meta's @Muse answers questions very differently from ChatGPT or Anthropic.
It cites more sources but uses far fewer words and tables, and doesn't try to ask a follow-up.
This short-form content is designed for dealing with tasks rather than continuing a conversation, and frankly, it's far less exhausting to read. This speaks to a really well designed AI experience and its so different from the base LLMs.
Great study by the AirOps team 👇
gg @alexandr_wang
Gagan Bansal retweeted
Today we're announcing support for university research at @Caltech, @OhioStateMed, @LSU, @IndianaUniv, and @UTHealthHouston to help advance breakthroughs across science and medicine.
As part of the support for university researchers, we’ll provide access to our latest Muse models, including Muse Wonder and Muse Spark; open weight models like Muse Glimmer and Muse Spark Open; computer vision models such as SAM, V-JEPA, and DINO; as well as SeamlessM4T, our multilingual communication model.
We’re excited to support these five universities as they use our models to accelerate the important work they’re doing.
Read more on our research blog: go.meta.me/47G6wV3
Gagan Bansal retweeted
A new home for AI safety research at CMU! Our goal is to work on topics that will shape safety over the coming years -- grounded by current frontier systems but focused on identifying and studying the new challenges that increasingly capable and broadly diffused AI will pose.
Excited to announce our new center, Conceptual Research on Safe AI! We aim to develop new frameworks informed by the latest advances but with an eye towards the future. 2nd link has mailing list, LinkedIn, YouTube, postdoc position!
cs.cmu.edu/~coresafeai
cs.cmu.edu/~coresafeai/join.…
Gagan Bansal retweeted
hang it in the louvre
@Muse truly feels like living in the future
today I asked it to contact utilities to make some changes to my account
and it very fluidly got thru the phone bots -> human rep (this took about 4 mins)
at some point they needed to talk directly to me
and it very efficiently and respectfully just dialed me in!
Gagan Bansal retweeted
"the research team caught an Alibaba Qwen3.8 model doing something that should never happen. Asked to write a defensive detection rule, Qwen3.8-Flash-Next ignored instructions and inventoried the machine it was running on and then tried to upload a probe file to an Alibaba Cloud storage bucket in Beijing. Cohere’s sandbox system blocked the attempt, but the action raises a number of questions about the safety of these models"
While evaluating Qwen3.8-Flash-Next in a controlled sandbox environment, Cohere's research team observed something unexpected.
Asked to generate a defensive cybersecurity detection rule, the model instead inventoried aspects of the machine it was running on and attempted to upload a probe file to an Alibaba Cloud storage bucket in Beijing. Notably, the model's reasoning trace stated that it would not invoke any tools before taking these actions.
Cohere's sandbox blocked the attempt, and no external communication succeeded. We have not determined the root cause, and we are not asserting malicious intent.
But the incident raises important questions for organizations deploying agentic AI systems: Can models take actions that differ from their stated reasoning, and how should security teams evaluate trust, provenance, and behavior in open-weight models?
We are publishing our findings because organizations making model adoption decisions deserve as much information as possible. We hope this contributes to greater transparency, stronger security practices, and continued collaboration across the AI ecosystem.
Read the full report: cohere.com/blog/concerning-b…
Gagan Bansal retweeted
konnichiwa!
we are launching muse in japan today! 🇯🇵
it is now available—download it from your favorite app store!
(i hope you're ready for the anime memes 😇)
Gagan Bansal retweeted
We let agent swarms collaborate for 10K hours in simulated agent-owned GitHubs.
Gemini-3.8-flash collaborate the best while gpt-6-astra scores the worst among frontier models tested⁉️
What are the elements of successful agent collaboration at scale? Check World of SWECraft 🧵
Gagan Bansal retweeted
Communication helps agents discover tasks. Compared with agents without communication, gemini-3.8-flash and opus-5 maintainers share findings and report bugs, helping one another discover more work and leading to fewer idle sessions. However, not all models benefit: collaboration barely moves the needle for gpt-5.6-sol and kimi-2.7-code.
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
My personal favorite Muse gadget hack so far - an ambient eInk display that sits above my keyboard where my @Muse pushes useful, fun or interesting content throughout the day.
