Joined July 2007
- Tweets 1,152
- Following 1,333
- Followers 1,118
- Likes 4,547
13 Photos and videos
Pinned Tweet
4 Nov 2025
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!
ALT Long-form Speech Generation with Spoken Language Models. ICML 2025 Oral. Recent work from our team on long-form speech language models with state-space models.
1
11
105
17,730
RJ Skerry-Ryan retweeted
Jun 13
I know comparing modern society to Idiocracy is really played out but man
637
7,495
67,959
2,416,929
Jun 9
sadface :(
Jun 9
You're not even allowed to ask Fable about basic biology questions, let alone anything that could potentially be dangerous.
7
368
RJ Skerry-Ryan retweeted
Introducing Gemini 3.5 Flash Live Translate, our real time speech to speech translation model which supports more than 70 languages (both in and out), and is so natural.
It is available in the Gemini API, AI Studio, & Google Translate right now coming soon to Google Meet!!
203
344
4,035
446,858
RJ Skerry-Ryan retweeted
The closure of @USAID by 20-something DOGE bros (who probably thought "screwworm" was a hilarious joke) will haunt us for years to come.
92
1,990
6,117
280,296
RJ Skerry-Ryan retweeted
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
huggingface.co/magenta-commu…
1
15
102
34,110
Jun 4
ICYMI SequenceLayers is getting an MLX backend, thanks to the Magenta team. ❤️ Thanks to @DoItRealTime @JulianSlzr @KehangHan
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!
1
7
213
RJ Skerry-Ryan retweeted
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!
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 🧵
14
29
274
43,955
RJ Skerry-Ryan retweeted
Jun 4
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!
52
90
883
103,634
RJ Skerry-Ryan retweeted
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 🧵
21
95
493
109,501
RJ Skerry-Ryan retweeted
Jun 3
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)🧵
9
51
466
85,474
RJ Skerry-Ryan retweeted
May 30
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 🎸
May 29
Help build a future of AI in music that's live, interactive, and deeply human.
Join Google DeepMind's Magenta team in Boston and get access to a generative model you can actually play as an instrument, and build your own AI instrument, plugin, or performance.
📍 Boston Music Technology Hackathon
1
7
53
5,064
RJ Skerry-Ryan retweeted
May 29
sorry it blew up, but for explosion fanatics, this is an all-time explosion caught on camera x.com/SawyerMerritt/status/2…
705
4,997
54,163
2,563,897
RJ Skerry-Ryan retweeted
May 19
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 👇
122
102
1,539
70,786
RJ Skerry-Ryan retweeted
May 19
Big improvements in quality and capabilities from the Omni team, excited to see how we translate this to progress for embodied AGI
May 19
We’re dropping Gemini Omni: our first step towards a model that can create anything from anything - starting with video.
It combines Gemini’s intelligence with our generative media systems - representing a leap forward in world understanding, multimodality, and editing 🧵
3
7
51
23,247
RJ Skerry-Ryan retweeted
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.
May 19
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!
7
17
102
5,716
May 19
icymi, this is a flash model. and it's really, really fast.
May 19
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!
113
May 19
yes, it runs doom.
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
1
82
RJ Skerry-Ryan retweeted
May 19
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!
222
542
5,961
1,285,485
RJ Skerry-Ryan retweeted
May 19
3.2 quadrillion tokens a month and still growing :)
58
55
1,284
54,303