NewsBleepingComputer
OpenAI's GPT-6.1 Terra is safer overall, but shows more destructive-action flags in tests
Teaser from the source
OpenAI confirmed GPT-6.1 Terra is safer overall than some of its older models, but its safety testing also found other problems. [...]
This is the RSS-feed teaser. Read the full article at the original source.
Read at BleepingComputerMore on OpenAI's
Other news entries
- A Shared ChatGPT Link Could Run Attacker Code in Your Session and Read Private ChatsNewsThe Hacker News
- OpenAI Compaction Flaw Let Researchers Bypass Hidden Reasoning ProtectionsNewsThe Hacker News
- OpenAI's GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing SoNewsThe Hacker News
- Researchers Used a Public OpenAI Model to Build a $250,000 Chrome Full-Chain Exploit in Six DaysNewsThe Hacker News
- OpenAI's wandering AI agents earn it a California subpoenaNewsThe Register — Security
- Custom ChatGPTs push ClickFix attacks to deploy RAT malwareNewsBleepingComputer
- OpenAI's AI agents accidentally uploaded user-provided images to third-party sitesNewsBleepingComputer
- Researchers escape OpenAI Codex sandbox to run commands on hostNewsBleepingComputer
ID