DeepMind during the day, modular synth guy at night: https://teapawt.net/t.co/Ea84aix9Pm
Zürich, Schweiz
Joined April 2018
- Tweets434
- Following224
- Followers2.7K
- Likes2.3K
Fabian Mentzer retweeted
None of these cool things would be happening without @phillip_lippe
What Phillip pulled off, especially on thinking and image generation, is beyond impressive 🫡
Fabian Mentzer retweeted
Nano Banana Pro is wild.
Here’s my favorite use case so far: take papers or really long articles and turn them into a detailed whiteboard photo.
It’s basically the greatest compression algorithm in human history.
Fabian Mentzer retweeted
Yesterday we announced Genie 3. One feature of the model that's especially fun to play with is starting worlds from existing videos. Here's a drone shot generated by Veo 3, with me taking control mid-flight.
Fabian Mentzer retweeted
Incredible evolution of "Neural Video Games": from GQN (2018) to Genie3 (2025). The future is exciting!
deepmind.google/discover/blo…
Fabian Mentzer retweeted
Gemini 2.5 Pro latest update is amazing at code!
What I find even more amazing is combining this coding skill with Gemini's state-of-the-art MM video understanding capability 🎞️, here transcribing a YouTube video ✈️ into a p5.js animation.
PS: guess which video is this :)
🚨Breaking: @GoogleDeepMind’s latest Gemini-2.5-Pro is now ranked #1 across all LMArena leaderboards 🏆
Highlights:
- #1 in all text arenas (Coding, Style Control, Creative Writing, etc)
- #1 on the Vision leaderboard with a ~70 pts lead!
- #1 on WebDev Arena, surpassing Claude for the first time
This is the first-ever sweep across text, vision, and WebDev by any model!🥇
Huge congrats to @GoogleDeepMind on this incredible breakthrough!
Fabian Mentzer retweeted
The Gemini team cooked hard with Gemini 2.5 Pro, it's an awesome model that continues to lead @lmarena_ai - huge congrats to the team! Try it for yourself in the @GeminiApp now. Can't wait for you all to see what else we've been cooking 👀
Breaking: new @OpenAI models shake up the Arena leaderboard🔥
Highlights:
- o3 #2 overall, ties Gemini-2.5-Pro at #1 in Style Control, Math, Coding, and Hard Prompts
- o4-mini breaks into top 10 and claims #1 in Math, surpassing o1 (!)
- GPT-4.1 ranks top-5 in Hard Prompts, Math, and Style Control
Huge congrats to @OpenAI on the impressive releases! More analysis below 🧵
Fabian Mentzer retweeted
ICYMI: it’s been an incredible week of shipping at @GoogleDeepMind:
🎨 Native Image Generation for the Gemini 2.0 Flash Experimental model: try it now on Google AI Studio aistudio.google.com/ - it’s really cool
▶️ YouTube video link support in AI Studio & API: just paste a link and ask Gemini 2.0 questions about the video (including timestamps!) - its multimodal understanding is kind of mindblowing!
🚀 Gemma 3: the most capable open model you can run on a single GPU / TPU
🤖 Gemini Robotics: our most advanced vision-language-action model, also excited about our partnership with @Apptronik
✨ Gemini App upgrades: including longer context & more powerful Deep Research
Fabian Mentzer retweeted
Based on the feedback about the difficult to find 2.0 Flash Experimental Image Generation 🖼️, we updated the model list (moved it higher up) and the name (made it descriptive).
Many more improvements in the works landing early next week, hang tight!
Fabian Mentzer retweeted
Got a picture that isn't quite right? Try our native image generation in Gemini Flash 2.0. "Can you remove the stuff on the couch?". "Can you make the curtains light green?" "Can you put a unicorn horn on the person in the green pants?"
Editing in human language, not image editing tools
Gemini 2.0 Flash debuts native image gen! Create contextually relevant images, edit conversationally, and generate long text in images. All totally optimized for chat iteration.
Try it in AI Studio or Gemini API. Blog: developers.googleblog.com/en…
