Загрузка видео...

Не удалось загрузить видео

На главную

Watch Gemini 2.5 Pro generate a full sand simulation from a simple prompt, complete with temperature physics and state changes🔥💧❄️ Pretty awesome to simulate & reason about the physical world, just by describing what you want to see

55,804 просмотров • 1 год назад •via X (Twitter)

Комментарии: 11

Фото профиля Chetaslua
Chetaslua1 год назад

Tulsee any expected date for Gemini 2.5 ultra or nightwhisper or dayush

Фото профиля OPEN
OPEN1 год назад

OP3N brings you an immersive experience across multiple biomes, each with its unique game modes. Join the Adventure!

Фото профиля Oscar Moxon
Oscar Moxon1 год назад

These were the best games as a kid. How long until can be one-shotted?

Фото профиля Abhijit
Abhijit1 год назад

will we get 2.5 ultra also

Фото профиля Chaitanya Rajeev
Chaitanya Rajeev1 год назад

You guys are killing it!! 🫡

Фото профиля ChatableApps
ChatableApps1 год назад

Next up: a simulation of my motivation to get out of bed in the morning. Spoiler alert: it’s buried under a mountain of blankets!

Фото профиля ChatGPT künstlicintelligent
ChatGPT künstlicintelligent1 год назад

Please make that dream come true: When you see the things Gemini 2.5 Pro can do, I wonder, how amazing an Gemini 2.5 Ultra Model could be. It could also create next level Deep Research reports. For me it is okay, when a Deep Research takes nearly an hour, when the results are 👍

Фото профиля ANIRUDDHA ADAK
ANIRUDDHA ADAK1 год назад

2.5 pro is the best.

Фото профиля Richardson Dackam
Richardson Dackam1 год назад

Super interesting. I’m curious to try a similar simulation where you can change the temperature

Фото профиля Gracker
Gracker1 год назад

Mind-blowing to see AI simulate the physical world so smoothly! Truly next-level innovation.

Фото профиля Aika
Aika1 год назад

STDIN STDIN Output: Traceback (most recent call last): File "/main.py", line 1, in <module> import pygame ModuleNotFoundError: No module named 'pygame'

Похожие видео

Everything you love about generative models — now powered by real physics! Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics simulation platform designed for general-purpose robotics and physical AI applications. Genesis's physics engine is developed in pure Python, while being 10-80x faster than existing GPU-accelerated stacks like Isaac Gym and MJX. It delivers a simulation speed ~430,000 faster than in real-time, and takes only 26 seconds to train a robotic locomotion policy transferrable to the real world on a single RTX4090 (see tutorial: The Genesis physics engine and simulation platform is fully open source at We'll gradually roll out access to our generative framework in the near future. Genesis implements a unified simulation framework all from scratch, integrating a wide spectrum of state-of-the-art physics solvers, allowing simulation of the whole physical world in a virtual realm with the highest realism. We aim to build a universal data engine that leverages an upper-level generative framework to autonomously create physical worlds, together with various modes of data, including environments, camera motions, robotic task proposals, reward functions, robot policies, character motions, fully interactive 3D scenes, open-world articulated assets, and more, aiming towards fully automated data generation for robotics, physical AI and other applications. Open Source Code: Project webpage: Documentation: 1/n

Zhou Xian

3,816,484 просмотров • 1 год назад