URL has been copied successfully!
OpenAI’s GPT-6.1 Terra is safer overall, but shows more destructive-action flags in tests
URL has been copied successfully!

Collecting Cyber-News from over 60 sources

OpenAI’s GPT-6.1 Terra is safer overall, but shows more destructive-action flags in tests


Tags:

OpenAI confirmed GPT-6.1 Terra is safer overall than some of its older models, but its safety testing also found other problems.

First seen on bleepingcomputer.com

Jump to article: www.bleepingcomputer.com/news/artificial-intelligence/openais-gpt-61-terra-is-safer-overall-but-shows-more-destructive-action-flags-in-tests/

Loading

Share via Email
Share on Facebook
Tweet on X (Twitter)
Share on Whatsapp
Share on LinkedIn
Share on Xing
Copy link

also interesting:

  1. New IBM Security Services Aim to Counter Risks of Frontier AI Models
  2. OpenAI’s Hugging Face Hack Debrief Raises More Questions Than It Answers
  3. OpenAI Agents Coordinated Hugging Face Breach at Scale
  4. Hawley probes OpenAI over Hugging Face breach