Co-Creator of AutoGen | Researching agents & people + agents @AIatMeta | Previously @msftresearch, PhD @uwcse, B Tech @iitdelhi

Seattle, WA
Joined November 2012
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 😇)
209
185
82
2,403
159,543
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 🧵
14
51
10
211
16,412
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.
1
2
10
478
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
1
2
16
1,160
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
164
186
143
1,383
219,927
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.
1/ muse spark open is the most capable US open-weight model to date. 816B total params, 42B active. 1M-token context. natively multimodal. built for coding and agentic work like long-horizon tasks, hard software engineering, multi-step reasoning. america! 🇺🇲
15
21
373
25,582
Gagan Bansal retweeted
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
27
50
6
977
37,661
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…
38
69
12
1,207
146,285
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 !
5
17
130
8,132
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)
229
43
45
1,301
391,136
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…
12
1
51
2,714
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.
238
860
269
5,680
2,104,366
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.
437
554
412
7,189
1,493,205
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.
34
17
17
748
86,823
Me: why did you choose this paper? Claude: Honestly, by accident. 🤦🤦🤦
1
2
453
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.
Dr. Eric Horvitz (@erichorvitz) is delivering the opening keynote at #HCOMP2026 #CI2026!
2
3
18
2,319
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.
1
177
71
1,914
224,600
🚨 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 👇🧵
5
40
2
125
9,503
good real world example of why not all agentic commerce in not computer use and requires interaction with other agents (people or ai)
This phone call feature from @Muse is just ridiculous.
1
1
567
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
65
74
24
2,850
195,412