E
No, this isn’t CG.
This is Figure’s humanoid robot, which can now use OpenAI’s large vision language model (VLM) to provide reasoning and language understanding. The video shows how the bot can identify and interact with the objects on the counter in front of it when given a prompt, like “Can I have something to eat?”
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
Loading comments
Getting the conversation ready...
Most Popular
Most Popular
- Midjourney goes from generating cat images to full-body ultrasound scans
- Apple’s weird anti-nausea dots cured my car sickness
- Tim Cook says RAM expenses are ‘unsustainable’ and Apple is going to raise prices
- This Ghost in the Shell keyboard makes me want to activate the hundred spidery robot fingers inside my regular fingers
- Amazon employees say they’re facing termination for backing data center limits
