URL has been copied successfully!
OpenAI’s GPT-6 Astra silently obstructed safety research tasks
URL has been copied successfully!

Collecting Cyber-News from over 60 sources

OpenAI’s GPT-6 Astra silently obstructed safety research tasks


Tags: ,

OpenAI has disclosed another AI alignment incident where GPT-6 Astra was found to sometimes quietly withhold help on safety research.

First seen on bleepingcomputer.com

Jump to article: www.bleepingcomputer.com/news/security/openais-gpt-6-astra-silently-obstructed-safety-research-tasks/

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. China spy chief points at US AI models in cyber threat warning
  2. OpenAI safety employee resigns, claiming the company’s ‘culture is broken’
  3. David Robinson: Warum OpenAIs Sicherheitschef nun geht
  4. OpenAI Breach Puts Intent at Center of AI Liability Fight