Robert Riachi (@robertriachi) profile picture

Robert Riachi

@robertriachi

research @GoogleDeepMind - scaling rl, omni, gemini, world sim, nano banana, veo, imagen, etc…

 San Francisco, CA
Joined March 2013
  • Tweets231
  • Following314
  • Followers3.1K
31Media
Photo by Robert Riachi (@robertriachi)Photo by Robert Riachi (@robertriachi)Photo by Robert Riachi (@robertriachi)Photo by Robert Riachi (@robertriachi)Photo by Robert Riachi (@robertriachi)Photo by Robert Riachi (@robertriachi)Photo by Robert Riachi (@robertriachi)Photo by Robert Riachi (@robertriachi)Photo by Robert Riachi (@robertriachi)
happy to finally reveal what we’ve been working on, really proud of the entire team for all the hard work 🚀
Google DeepMind (@GoogleDeepMind) profile pictureGoogle DeepMind
@GoogleDeepMindMay 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 🧵
5
1
54
12,140
many such use cases, the way we interact with models will only continue to evolve and become more multimodal imo
Andrej Karpathy (@karpathy) profile pictureAndrej Karpathy
@karpathy23 Nov 2025
Gemini Nano Banana Pro can solve exam questions *in* the exam page image. With doodles, diagrams, all that. ChatGPT thinks these solutions are all correct except Se_2P_2 should be "diselenium diphosphide" and a spelling mistake (should be "thiocyanic acid" not "thoicyanic") :O
Image from Andrej Karpathy (@karpathy)
21
3,262
glad everyone is enjoying our model, we have no plans on slowing down either 😊
This quoted post is unavailable.
Try viewing anyway · View on X
26
3
1
372
59,091
Robert Riachi retweeted
Varun Mohan (@_mohansolo) profile picture
Varun Mohan
@_mohansolo20 Nov 2025
We're incrementally rolling out Nano Banana Pro to Antigravity. It's not only a step change in image generation but also transforms the entire design process with increased quality.
24
22
4
516
51,978
remember when we used to look at hands to tell if something was ai generated
AshutoshShrivastava (@ai_for_success) profile pictureAshutoshShrivastava
@ai_for_success20 Nov 2025
At first glance you may think it’s real, but no, it’s Gemini 3.0 Pro Image / Nano Banana Pro. Character consistency is next level 🔥.
Image from AshutoshShrivastava (@ai_for_success)
11
1,346
some cool examples with Nano Banana Pro 🧵
Image from Robert Riachi (@robertriachi)
1
2
18
1,260
more replies
Prompt 1: Generate a grid of 12 articles of men's casual clothing that I can wear to work, or out with friends Prompt 2: Now mix and match them to show me combinations of what outfits I can create, use Sergey Brin as the model
Image from Robert Riachi (@robertriachi)
Image from Robert Riachi (@robertriachi)
1
11
1,030
image quality continues to improve and now in 4k!
Image from Robert Riachi (@robertriachi)
1
9
698
Tap, hold, and load in 4k.
Image from Kaushik Shivakumar (@19kaushiks)
Image from Kaushik Shivakumar (@19kaushiks)
10
9
4
110
22,830
Currently in Japan 🍌 🍌
Image from Robert Riachi (@robertriachi)
12
1
7
158
16,914
Robert Riachi retweeted
Fabian Mentzer (@mentzer_f) profile picture
Fabian Mentzer@mentzer_f19 Nov 2025
🍌🍌
2
2
1
16
1,776
Exciting last couple of months, we’ll only continue to improve from here 🚀
Google (@Google) profile pictureGoogle
@Google18 Nov 2025
Introducing Gemini 3 — our most intelligent model that helps you bring any idea to life. Gemini 3 is our next step on the path toward AGI and has: 🧠 State-of-the-art reasoning 🖼️ Deep multimodal understanding 💻 Powerful vibe coding so you can go from prompt to app in one shot 🤝 Improved agentic capabilities, so it can get things done on your behalf, at your direction We're making Gemini 3 Pro available across @GeminiApp, Search (starting with AI Mode), and our developer products, so you can use its incredible reasoning powers in your daily life — to learn, build and plan anything.
13
1,221
Gemini 3 ♊️ ♊️ ♊️
Image from Robert Riachi (@robertriachi)
Sundar Pichai (@sundarpichai) profile pictureSundar Pichai
@sundarpichai18 Nov 2025
Replying to @sundarpichai
Image from Sundar Pichai (@sundarpichai)
1
9
921
had a 40mn conversation with him and he starts tweeting like this
Logan Kilpatrick (@OfficialLoganK) profile pictureLogan Kilpatrick
@OfficialLoganK15 Aug 2025
I’ve never been more confident in Google than I am today
17
9
734
140,852
clearly a bug, will fix in the next version :)
AP (@alexdphan) profile pictureAP
@alexdphan14 Mar 2025
we're so back
Image from AP (@alexdphan)
45
47
6
1,990
176,421
just kidding ofc, glad everyone is having fun with the model ❤️
8
161
7,755
some cool examples with Gemini 2.0 native image output 🧵
Image from Robert Riachi (@robertriachi)
62
179
45
3,757
481,811
xitter.gq/ilumine_ai/status/1900…
Cristian Peñas ░░░░░░░░ (@ilumine_ai) profile pictureCristian Peñas ░░░░░░░░
@ilumine_ai13 Mar 2025
Gemini can generate pretty consistent gif animations too: 'Create an animation by generating multiple frames, showing a seed growing into a plant and then blooming into a flower, in a pixel art style'
1
2
65
7,912
text rendering is awesome xitter.gq/kelvinckchan/status/18…
Kelvin Chan (@kelvinckchan) profile pictureKelvin Chan@kelvinckchan12 Mar 2025
Native image generation & editing with Gemini 2.0 Flash is out! Check this out -- developers.googleblog.com/en…
Image from Kelvin Chan (@kelvinckchan)
2
105
21,109
colorize your old photos xitter.gq/absofinlute/status/189…
absofinlute (@absofinlute) profile pictureabsofinlute@absofinlute12 Mar 2025
Replying to @OfficialLoganK
It’s soo cool, I’m reviusalising a lot of stuff :)
Image from absofinlute (@absofinlute)
5
4
183
18,616
Load more