DALL·E 2 Pre-Training Mitigationsby@whatsai

DALL·E 2 Pre-Training Mitigations

tldt arrow
EN
Read on Terminal ReaderPrint this storyRead this story w/o Javascript

Too Long; Didn't Read

Most artificial intelligence models aren’t open-source, which means we, regular people like us, cannot use them freely. This is what we will dive into in this video... The most well-known, Dall-e 2, can be used to generate images from random prompts. The data used to train such models as well coming from random images on the internet pretty pretty. We will look into what they are trying to mitigate risks and how they are filtering out violent and sexual images from the internet.

Company Mentioned

Mention Thumbnail
featured image - DALL·E 2 Pre-Training Mitigations
Louis Bouchard HackerNoon profile picture

@whatsai

Louis Bouchard

About @whatsai
LEARN MORE ABOUT @WHATSAI'S EXPERTISE AND PLACE ON THE INTERNET.
react to story with heart

RELATED STORIES

L O A D I N G
. . . comments & more!
Hackernoon hq - po box 2206, edwards, colorado 81632, usa