Conversation

Just in time
Quote Tweet
We’ve developed two neural networks which have learned by associating text and images. CLIP maps images into categories described in text, and DALL-E creates new images, like this, from text. A step toward systems with deeper understanding of the world. openai.com/multimodal/
Image
1
Yes! I spotted the DALL-E one and *love* the weird combinations it comes up with. I would kill to see GPT-3 try to visualise some of these. Are they open for use in any capacity? Couldn’t find the “How to use this AI 101 for n00bs” link on their post 😅
A+ I've mostly been living in Reactland, and pretty great not having to deal with useState / useEffect / useRef Component-level scoped CSS feels so much better than CSS-in-JS Now waiting patiently for the stable version of SvelteKit 😎 Have you played with it yet?
1
2
Show replies