shipfeedAI news, curated daily

01:14:33 CET
21 MAY01:14:33shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

DALL·E 2 pre-training mitigations

OpenAI details pre-training mitigations applied to DALL·E 2 to reduce risks from powerful image generation and prevent content policy violations.

Jun 28 · · primary fetch1 sourceupdated Jun 28 ·

In order to share the magic of DALL·E 2 with a broad audience, we needed to reduce the risks associated with powerful image generation models.

To this end, we put various guardrails in place to prevent generated images from violating our content policy.

read full article on openai.com
§ sources1 publication · timeline below
  1. openai.comDALL·E 2 pre-training mitigationsprimary