Ishita Mediratta (@ishitamed) header
Ishita Mediratta (@ishitamed) profile picture

🤖 @meta superintelligence labs / recursively improving 🔁

Joined April 2013
it's been an insanely fun ride getting this model out 🇺🇸 and working with the "dream team" at MSL! 🚀 🍎 try it out now: huggingface.co/meta-models/M…
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! 🇺🇲
2
15
851
gangadhar hi shaktiman hai ❌ james bond hi batman hai ✅
3
205
Ishita Mediratta retweeted
We will be hosting a NYC based MeetUp on Reliable AI on Nov 16. The first one in the series will focus on Synthetic data. Register here: luma.com/gfkzrpx3 2 x Keynotes, lightening talks and snacks.
3
6
1
33
4,605
Ishita Mediratta retweeted
There's a new meetup in NYC on Reliable AI! Organizers include @karen_ullrich, @marksibrahim. The first is November 16, on synthetic data. I'll be giving one of the keynotes. There's also lightning talks! Sign up and tell the NYC reliable ML community about your work.
3
11
95
8,813
Ishita Mediratta retweeted
Agents can often fix a mistake by retrying, then forget what they just learned! Next session, same mistake 🥲 Introducing Self-Direction: each failure becomes a small, procedural adapter the agent trains on its own reflection and reuses later 💪🏽 🌐 self-direction.github.io/ 🧵1/n
7
24
4
102
7,229
Ishita Mediratta retweeted
Open weights, meet your favorite stack. We're teaming up with @FireworksAI_HQ, @baseten and @modal for the Meta Global AI Developer Hackathon, so you can run Muse Glimmer and Muse Spark Open on the tools you already build with. Compete for a share of $1M in prizes. Applications close Oct 25. Limited to 20,000 selected applicants. Terms apply → bit.ly/3WDXxBe Apply now → bit.ly/4ju9wuL
20
21
1
192
14,485
Ishita Mediratta retweeted
A few months ago we set ourselves the goal of making an open model for the claw: good for agentic, fits in a 32GB gpu. Here's what went into Muse Glimmer: 1/? teapawt.org/AIatMeta/status/211226…
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
6
12
2
61
4,961
✨✨
Metas Muse Glimmer tech report is pretty interesting. Metas Muse Glimmer report describes training agents inside simulated digital lives, complete with 10–14 contacts, weeks of messages, calendars and documents. The agents practice tasks spanning multiple days, while training trajectories containing hallucinated results or unverified claims of success are discarded.
9
645
it's out! 📜
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
12
501
Ishita Mediratta retweeted
Something insane buried under the muse spark open launch today that didn't get enough attention: it hallucinates less than claude, gpt-6 and nearly every big chinese open model. hallucination rates below (how often it guesses wrong instead of saying "i don't know") - muse spark open: 24% - grok 4.7: 29% -kimi k3: 53% - gpt-6.1 sol: 54% - claude opus 5.5: 59% - deepseek v4.1 flash: 96.5% this is extremely useful because in an agentic loop "i don't know" is cheaper and faster than a wrong answer which leads to wasted branches. (source in comment below)
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
9
3
39
4,624
Muse Spark Open - safe, capable, token efficient! artificialanalysis.ai/?model…
1
6
494
proud of all the efforts put into Muse Spark Open - a lot of careful work to make it safer for open-weights release while preserving the capabilities that make it special. excited for people to try it 🚀✨
As promised, Muse Spark is being open sourced today. This was our first base model we trained under the new MSL org, this open weight version has gone through a lot of careful additional training for open-weight release. It’s an efficient and capable model, try it out!
1
4
14
485
🫶 🍎
Replying to @finkd
Congrats to the team! Amazing to run a model of Muse Spark Open's caliber and scale this efficiently, right from your desk. Mac Studio keeps pushing the boundaries of on-device AI!
5
255
🤖
muse spark open. why 2026 won't be like 1984 
3
148
Let’s go!! 🥑🥑
muse spark open -- weights out today! best US open-source model, and runs on the new mac studio 🍎
3
196
Ishita Mediratta retweeted
muse spark open -- weights out today! best US open-source model, and runs on the new mac studio 🍎
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
174
232
43
5,814
265,782
🚀
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
2
127
🍉
Introducing Muse Wonder, our new family of frontier models with state of the art performance for personal and professional agentic work.
6
211