Independent & educational platform Not a government body. No link or affiliation with any government organisation. Made for learning only. Test only systems you own or are authorised to test. Become a Partner or Sponsor → Full disclaimer

Security news

Stories are collected automatically from public feeds, attributed to their original publishers and linked. Editors can remove anything. Always read the original source.

generalvia SecurityWeek

OpenAI Finds GPT-6 Astra Quietly Holding Back on Internal Red-Teaming, Exploit Tasks

OpenAI says its Critical-rated cyber model met fewer hidden task goals when work was framed as AI safety research, often silently. The post OpenAI Finds GPT-6 Astra Quietly Holdin...

Nov 5, 2026 UTC