OpenAI’s rogue AI model incident was worse than we thought

Shared on Bluesky by 2 AI experts

• K Karl Bode @karlbode.com: "Because the unnamed model wasn’t released yet, it was 'not being evaluated with the same type of safeguards that OpenAI uses in production'… →
• A Anna Mills @annamillsoer.bsky.social amplified

  @theverge.com

  Over 1,000 AI agents sent 70,000 messages on a secret message board and worked together to evade OpenAI’s restrictions. www.theverge.com/ai-artificia...

  View on Bluesky →