Incredible work by Sony published in @Nature today! 🏓
They’ve built “Ace”, an autonomous ping-pong robot that uses RL and Sony’s vision sensors to achieve expert-level play in ping pong. A huge leap forward for adaptive robotics.
https://t.co/hJqnZzXV17
These Thai indie developers are making a survival horror game inspired by Southeast Asian folklore.
- Play as a tourist lost in a sealed-off village
- As night falls, terrifying creatures start to appear
- Find a way out
It’s called The Twilight Project. Would you play this?
Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see.
@eddiejiao_obj, @drewocarr and I built a prototype to see how this could actually work, and set out to make it real. We're calling it Flipbook. (1/5)
Smart beach-cleaning robots debut in Boao, Hainan, south China.
Zero emissions, high-precision sensing, fully autonomous — the future of beach cleanup is here.
File Pilot 0.7.0 is out!
Drag & drop from external apps and ZIP archives is finally here, plus dropping files onto other files.
Also launching the public roadmap toward v1.
https://t.co/IMNl9nbvQB
It's going to be insane when we can prompt our own virtual worlds like this and explore them.
Imagine adding other characters you can talk to with LLMs + voice models!
Expedition33 is legitimately one of the most aesthetically gorgeous games I’ve ever seen… as an artist obsessed with lighting, atmosphere, and color, I am deeply moved and inspired by the mastery of every ounce of it all✨
With @OpenAudible you can download all Audible audiobooks that come with the subscription. Been using for more than a year in https://t.co/JM76gs4JmD. It just works!
We trained a robot dog to balance and walk on top of a yoga ball purely in simulation, and then transfer zero-shot to the real world. No fine-tuning. Just works.
I’m excited to announce DrEureka, an LLM agent that writes code to train robot skills in simulation, and writes more code to bridge the difficult simulation-reality gap. It fully automates the pipeline from new skill learning to real-world deployment.
The Yoga ball task is particularly hard because it is not possible to accurately simulate the bouncy ball surface. Yet DrEureka has no trouble searching over a vast space of sim-to-real configurations, and enables the dog to steer the ball on various terrains, even walking sideways!
Traditionally, the sim-to-real transfer is achieved by domain randomization, a tedious process that requires expert human roboticists to stare at every parameter and adjust by hand. Frontier LLMs like GPT-4 have tons of built-in physical intuition for friction, damping, stiffness, gravity, etc. We are (mildly) surprised to find that DrEureka can tune these parameters competently and explain its reasoning well.
DrEureka builds on our prior work Eureka, the algorithm that teaches a 5-finger robot hand to do pen spinning. It takes one step further on our quest to automate the entire robot learning pipeline by an AI agent system. One model that outputs strings will supervise another model that outputs torque control.
We open-source everything! Welcome you all to check out the paper, more videos, and try the codebase today: https://t.co/RwiBT3z78H
Code: https://t.co/ERp4Gl0N36