{"id":35608,"date":"2022-04-18T16:26:23","date_gmt":"2022-04-18T20:26:23","guid":{"rendered":"https:\/\/mjtsai.com\/blog\/?p=35608"},"modified":"2022-10-07T16:27:11","modified_gmt":"2022-10-07T20:27:11","slug":"dall-e","status":"publish","type":"post","link":"https:\/\/mjtsai.com\/blog\/2022\/04\/18\/dall-e\/","title":{"rendered":"DALL-E"},"content":{"rendered":"

Ben Thompson<\/a> (Hacker News<\/a>):<\/p>\n

\n

Last week OpenAI released DALL-E 2<\/a>, which produces (or edits) images based on textual prompts; this Twitter thread from @BecomingCritter<\/a> has a whole host of example output[…]<\/p>\n

[…]<\/p>\n

[C]reating games, particularly their art, is expensive, and the expense increases the more immersive the experience is. Social media, on the other hand, is cheap because it uses user-generated content, but that content is generally stuck on more basic mediums — text, pictures, and only recently video. Of course that content doesn’t necessarily need to be limited to your network — an algorithm can deliver anything on the network to any user.<\/p>\n

What is fascinating about DALL-E is that it points to a future where these three trends can be combined. DALL-E, at the end of the day, is ultimately a product of human-generated content, just like its GPT-3 cousin. The latter, of course, is about text, while DALL-E is about images. Notice, though, that progression from text to images; it follows that machine learning-generated video is next. This will likely take several years, of course; video is a much more difficult problem, and responsive 3D environments more difficult yet, but this is a path the industry has trod before[…]<\/p>\n

[…]<\/p>\n

Machine learning generated content is just the next step beyond TikTok: instead of pulling content from anywhere on the network, GPT and DALL-E and other similar models generate new content from content, at zero marginal cost. This is how the economics of the metaverse will ultimately make sense: virtual worlds needs virtual content created at virtually zero cost, fully customizable to the individual.<\/p>\n<\/blockquote>\n\n

Bram Adams<\/a> (via Hacker News<\/a>):<\/p>\n

\n

DALL·E is intuivitely understandable on an emotional level while simultaneously being quite unintuitive on a logical level.<\/p>\n

[…]<\/p>\n

Here are some things I’ve picked up so far that I think can help push the dialogue around DALL·E forward.<\/p>\n<\/blockquote>\n\n

Previously:<\/p>\n