But is it art?
Key Takeaways
Move over, Picasso.
A new neural connection can draw images based on text.
Ai-Da
The system uses a neural web connection thats been trained on billions of pictures and text examples.
The data is then processed by a natural language model and is trained to produce images from text.
GPT-3 was trained using half a trillion words of internet text and can produce surprisingly lifelike text.
Teaching a machine to understand language well enough to draw a picture is a very significant achievement.
“The initial creativity comes from the human who constructed the task,” Schwartz said.
Robot Detective Work?
A machine can experiment with this data and object combination much faster than a human artist.
“These visualizations could then be integrated to create a more precise image of lost evidence.
This visualization could be enriched by integrating previous imagery of the location prior to the crime.”
Several other AI-driven programs can produce art.
For example,Ai-Dauses a robotic arm system and facial recognition technology paired with artificial intelligence to create art.
After taking a look at DALL-Es work, I understand Elgammals point that the AI-created images arent art.
On the other hand, they are better than any art I could create.
So, really, whats the difference?
