OpenAI reports DALL-E 2 safeguards across three million generated images
OpenAI reported more than three million DALL-E 2 images generated by early users while deploying improved text filters and automated detection and response for policy violations.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why it moved the index
The update documented safeguards operating at meaningful real-user scale, including enhanced prompt filtering and automated policy enforcement. Limited weekly onboarding and a low flagged-image rate constrained both deployment risk and demonstrated control magnitude.
Assessment history
-
R1
Away 35 · confidence 97
New May 2022 deployed generative-image safeguard event, distinct from the April model preview.
12 Aug 2026
Share this page
-
DoomBench assesses “OpenAI reports DALL-E 2 safeguards across three million generated images” as evidence moving away from doom, with magnitude 35 and confidence 97 out of 100 in the safety and alignment category.
-
The DoomBench assessment of “OpenAI reports DALL-E 2 safeguards across three million generated images” is based on reporting from OpenAI and records the editorial rationale, source quality, attribution, and revision history.
-
DoomBench summarizes “OpenAI reports DALL-E 2 safeguards across three million generated images” as follows: OpenAI reported more than three million DALL-E 2 images generated by early users while deploying improved text filters and...
https://www.doombench.com/news/openai-reports-dall-e-2-safeguards-across-three-million-generated-images-2022-05-18