Google DeepMind. Gemini Omni, Veo 3, Veo 2, Veo 1, Phenaki, and more.
California, USA
Joined December 2007
- Tweets3.1K
- Following1.3K
- Followers1.5K
- Likes16.3K
Pinned Tweet
Gemini Omni is available! Proud to work in this amazing team
Hernan Moraldo retweeted
Excited to share Omni 1.2 Flash!
Had so much fun making this model faster and cheaper to run! Can’t wait for you to try longer, more creative generations and see what you come up with!
Meet Gemini Omni 1.2 Flash, our updated video generation model from @GoogleDeepMind 🎬
Get stronger consistency, more creative control, and faster, more cost-effective video creation at scale:
⚡ Fast & 30% lower cost: Draft at 360p or 720p ($0.07/s) and upscale to 1080p or 4K
⏱️ Longer clips: Generate and edit videos up to 15s, or pick any exact length from 3s to 15s
💬 Edit in conversation: Swap backgrounds, subjects, or lighting turn by turn without starting over from scratch
🗣️ More natural speech: Create fluid, multi-speaker dialogue with clearer lip-sync
🎬 More controllable shots: Direct continuous camera moves with fewer jump cuts
See these updates in action ↓
Hernan Moraldo retweeted
Omni Flash 1.2 also has great improvements on T2V and I2V on @arena!
Meet Gemini Omni 1.2 Flash ⚡️
We’ve made the model more cost-effective, bumped the video generation and editing limit up to 15 seconds, and made updates to how scenes hold together over time. We've also given character speech an upgrade, reduced visual glitches like jump cuts, and made sure the model stays even truer to any reference assets you upload.
So… what does all of that actually mean for you?
It gives you more room to tell your story. With up to 15 seconds to work with, you have more flexibility to create what you need — videos look more cinematic and smooth, offering stronger consistency that keeps objects anchored from start to finish. And when characters speak, the dialogue sounds more fluid and natural.
Creators and everyday users can start directing scenes and multi-turn edits in @FlowbyGoogle, generating 15-second clips at no additional cost in Google Vids, or creating 15-second videos in the @GeminiApp. Plus, for developers and businesses building with the API, we've dropped the price by 30% from the previous generation, making it available at just $0.07 per second for 720p video.
Watch the model in action as it turns a single style frame into a 4-shot, 15-second macro science explainer of a living beehive ↓
"Google’s Omni variants take all 3 top slots in Text-to-Video."
Big news: Gemini Omni 1.2 Flash by @GoogleAI debuts at #1 in both Text-to-Video and Image-to-Video, and #3 in Video Edit!
Gemini Omni 1.2 Flash landed #1 in Text-to-Video with 1541 pts. This is a +27 pt improvement from the previous Gemini Omni 1.1 Flash at #2 with 1514 pts.
With this release, Google’s Omni variants take all 3 top slots in Text-to-Video.
See the Image-to-Video and Video Edit results in thread.
Congrats to the @GoogleAI team on this release!
A new version of Gemini Omni is out!
Today we are rolling out Gemini Omni Flash 1.2, with:
- longer video generation (15 seconds)
- deeper cinematic controls for camera pov
- support for multi-turn conversation editing
- less visual drift
- 30% lower price than Omni Flash 1.1
Read more: blog.google/innovation-and-a…
Hernan Moraldo retweeted
I made the frontier models race each other in my sailing sim
every 5 secs they get the full state of the world (heading, speed, wind etc) and adjust their helm and sails
Argon won, Astra came second and Opus couldn't finish. for fun I threw in a lil qwen model.. it ran aground
Hernan Moraldo retweeted
⚡Iterating at lightning speed! Gemini 4 Carbon is SOTA across key benchmarks and combines frontier capabilities with deep safety & security research.
Hernan Moraldo retweeted
Gemini 4 Carbon is here!
It’s been a significant improvement for my work overall
I did say we'd be releasing our models periodically...introducing Gemini 4 Carbon, our next frontier model.
Following Argon's release just two weeks ago, Carbon shows the pace at which we’re pushing the frontier, it ranks #1 on the recently updated v5.0 of @ArtificialAnlys Intelligence Index at 59. It also leads across key cybersecurity evaluations scoring 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation, and 71.0% on CWE-bench for patching.
We’re seeing significant improvements in long-horizon tasks even compared to Argon, and we’ve strengthened frontier safeguards.
As we did with Argon, we’re going to roll it out gradually + responsibly. Some trusted cyber defenders will get access starting this week. We'll be expanding it to more partners through our Fairwind Program, ahead of wider availability soon, so hang tight!
Hernan Moraldo retweeted
i’ve found myself using Genie 4 to have conversations with younger versions of myself...
here’s me talking to myself just out of college. i was pretty naive, but not a whole lot has changed :)
Hernan Moraldo retweeted
With Genie 4, you can use natural language to modify a simulation in real-time
like changing the weather, moving the camera, or introducing a new person or object
and Gemini will contextually adapt your prompt to match the surrounding scene. Between your inputs, Gemini also monitors and steers the scene to keep the world progressing cohesively.
Hernan Moraldo retweeted
Happy to share our latest version of Genie, built on the foundation of Gemini Omni.
Genie 4 simulates worlds with native audio in real-time and at a significantly higher quality, especially for photorealistic scenes with dialog and speech.
Great work by an amazing team!
Hernan Moraldo retweeted
Excited to share Genie 4 today our most realistic and interactive world model:
- steer dynamic environments in real time, shaping events, camera angles, and actions
- generate native audio matched to the world, from realistic background sounds to characters who can converse in real time!
- simulate photorealistic scenes and real-world physics
- create more coherent multi-step events through reasoning from Gemini
We've started to roll out as a research preview to trusted testers. Coming soon to Google AI Ultra subscribers in Project Genie and early access partners via the Gemini API and AI Studio.
Hernan Moraldo retweeted
This is Genie 4, our most realistic and interactive world model yet. 🌐
Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.
Hernan Moraldo retweeted
Nintendo’s Shigeru Miyamoto, the acclaimed designer behind Super Mario and Zelda, has explained why he believes generative AI won’t make human creativity obsolete.
"There will always be a role left for us to play."
videogameschronicle.com/news…
Tim's right, but also, he's one of the few people who's making the right moves to make the game industry stronger despite the challenges of this transition. This may not be apparent yet, but will be obvious soon.
Hernan Moraldo retweeted
The games we've long wanted, which didn't exist because they'd cost several times more to make than they'd earn back, will soon become possible. As will the games developers wanted to build, but couldn't with the resources available. It'll be a new golden age of gaming.
Hernan Moraldo retweeted
Gemini 4 Argonのチームがついにエンダードラゴンを倒しました（マインクラフトの話です）。
Google DeepMindがAIエージェントたちに"エンダードラゴンを倒せ"とだけ伝えてゲームの世界に放り込んだところ、27時間14分で倒したそうです。
やり方は人間のプレイヤーそのものだったとのこと。
・エンダーマンは高さ3ブロックなので、天井2ブロックの小屋にこもって向こうから来させる
・エンダーアイを2か所から投げて飛ぶ向きを記録し、交点から要塞の場所を割り出す（誤差43m）
・ドラゴンに69回殺されたあと、「到着した足場で待つな」「止まっている時だけ近づけ」と全員向けのルールを書いて共有
4体のエージェントが1日以上かけて何千もの手順を崩さずに進め、仲間と教え合いました。
研究者らは、これこそは長い仕事を任せるコーディングエージェントに必要な素養と同じだとしています。
また、周りのブロックや敵の情報は数値で受け取っているので、画面を見て操作したわけではありません。
なお、費用はAPIの定価で約520ドルでした。
※エンダードラゴンはこのゲームの最後のボスで、素手の状態から道具を作り、別世界で材料を集め、地下の要塞を探し当てて、ようやくたどり着ける相手・・・とのことです
Hernan Moraldo retweeted
🤖 😊 This is VERY good news, if solid! (I haven't read the article yet; it's long.)
I advocated this as "the most promising short-term technical approach to increased AI safety" in the "Fight DOOM AI with SCIENCE! and ENGINEERING!!" chapter of my book. nitter.gq/nickcammarata/status/2…
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works
already-clean.goodfire.com/
