RJ Skerry-Ryan

🌮🤖 Speech and language modeling researcher.
Principal SWE @ Google Deepmind.
♊🌊 Gemini Audio and Astra core team.

[RJ Skerry-Ryan @rustyryan]

My team in GDM Frontier AI is hiring (Mountain View). If you're a researcher interested full duplex modeling, multimodal LLMs (Gemini), modality gap, joint speech/text modeling, PGMs, streamable generative models, and representation learning for language modeling -- DM me!

[Jeremy Konyndyk @JeremyKonyndyk]

The closure of @USAID by 20-something DOGE bros (who probably thought "screwworm" was a hilarious joke) will haunt us for years to come.

[RJ Skerry-Ryan @rustyryan]

@_arohan_ People still play go and chess... I'll still be enjoying my computer hobbies even when it's "pointless". It might even be more fun when it's absolutely out of the question that it's commercially valuable 😂

[apolinario @ CVPR @multimodalart]

I' m so addicted to @GoogleMagenta RealTime 2 🎹

so to justify playing with it 24/7 I ported the real-time apps to @huggingface Spaces 🤗 (and ported the entire lib to pytorch/transformers too)

Play live in real time on
https://t.co/5JSl6KCNnU

[RJ Skerry-Ryan @rustyryan]

ICYMI SequenceLayers is getting an MLX backend, thanks to the Magenta team. ❤️ Thanks to @DoItRealTime @JulianSlzr @KehangHan

[Google Magenta Project @GoogleMagenta]

MRT2 runs on MacBooks by leveraging the MLX runtime to efficiently execute it on Apple Silicon.

The framework has been a fantastic link between Python and C++, and thanks to @awnihannun for offering guidance on the MLX integration!

[Ilaria Manco @Ilaria__Manco]

Really proud to share something we’ve been working on for a while: Magenta RealTime 2 (MTR2), a live music model that is highly interactive (MIDI, audio, text, lots of parameters) and low-latency (~200ms end-to-end), and runs locally on a MacBook!

[Omar Sanseviero @osanseviero]

Introducing Magenta RealTime 2 🎺

- Open model for live music generation
- Just 2.4B parameters, perfect for on-device
- Low latency control
- Control with audio, MIDI, and text

We're releasing it with a series of apps to experiment directly in Mac!

[Google Magenta Project @GoogleMagenta]

Introducing Magenta RealTime 2 (MRT2): the live music model you can play as an instrument.

MRT2 offers MIDI and prompt controls, and runs natively on a MacBook with <200ms latency.

Open weights. Open source inference engine. Suite of apps and plugins.

Hear what it can do and try it out for yourself below 🧵

[SemiAnalysis @SemiAnalysis_]

With the introduction of the TPUv8t, their new training focused TPU, Google unveiled a new scale-out network architecture called Virgo. Virgo is able to interconnect up to 134,400 chips with up to 47 Pbps of non-blocking bi-sectional bandwidth. (1/4)🧵

[Jesse Engel @jesseengel]

We've got a new model coming out next week! We've been having a lot of fun playing with it, and I hope you will too♥️

We'll be celebrating by presenting at the AI Music Summit at Berklee and helping teams at the hackathon afterwards build some wild new musical instruments 🎸

[RJ Skerry-Ryan @rustyryan]

@_arohan_ vicious, you're really breaking ELBOs here

[Hunter Weiss @Hunter_Weiss]

sorry it blew up, but for explosion fanatics, this is an all-time explosion caught on camera https://t.co/nt12WgCwc3

[Zvi Mowshowitz @TheZvi]

https://t.co/8oI3dxvl2F

[RJ Skerry-Ryan @rustyryan]

@willmcgugan @geminicli You have it backwards -- agy is the new cli (left), gemini-cli is deprecated (right).

[Jack Wotherspoon @JackWoth98]

Say hello to Antigravity CLI 🚀💻

🧑‍💻 - Written in Go for a snappy feel
✨ - Available with Gemini 3.5 Flash today
🤖 - Built for async workflows and subagents
⚒️ - Same tools and app server as Antigravity 2.0

Get started and install it today 👇

[Jack Parker-Holder @jparkerholder]

Big improvements in quality and capabilities from the Omni team, excited to see how we translate this to progress for embodied AGI

[Melvin Johnson @melvinjohnsonp]

Today, we introduced Gemini 3.5 Flash ⚡ Our most capable coding and agentic model — where "fast" and "best" aren't a tradeoff. Try it now across Antigravity, AI Studio, Gemini App, and AI Mode.

[RJ Skerry-Ryan @rustyryan]

icymi, this is a flash model. and it's really, really fast.

[Logan Kilpatrick @OfficialLoganK]

Welcome to Gemini 3.5 Flash, our most powerful model to date. It pushes the frontier of intelligence, speed, and cost putting 3.5 Flash in a class of its own.

We spent the last 6 months making sure Flash is great for real world use cases. It's available everywhere now!

[RJ Skerry-Ryan @rustyryan]

yes, it runs doom.

[Google @Google]

We asked our agents to build a working operating system from scratch using @Antigravity 2.0 and Gemini 3.5 Flash.

It took:
⏱️ 12 hours
🤖 93 parallel sub-agents
🔄 15k+ model requests
🧠 2.6B tokens processed
💸 Less than $1K in API credits

To build a functioning OS from scratch.

#GoogleIO

[Logan Kilpatrick @OfficialLoganK]

Introducing Gemini Omni 🔮........ Omni is our new model that can create anything from any input — starting with video (think Nano Banana but for video). Available in the Gemini App, Flow, and YouTube, with API support coming soon!

[Logan Kilpatrick @OfficialLoganK]

3.2 quadrillion tokens a month and still growing :)