OpenAI Designed GPT-5 to Be Safer. It Still Output... Wired

OpenAI Designed GPT-5 to Be Safer. It Still Outputs Gay Slurs

Wired August 13, 2025

The new version of ChatGPT explains why it won’t generate rule-breaking outputs. WIRED’s initial analysis found that some guardrails were easy to circumvent.

Comments 0

Log in to post a comment.

No comments yet. Be the first to comment!

Advertise with Us

Reach our audience with your ads