💻 Technology 3h ago · Mayank Parmar

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

BleepingComputer
Cybersecurity and malware threat reports
View Channel →
Source ↗ 👁 2 💬 0
OpenAI confirmed GPT-6.1 Terra is safer overall than some of its older models, but its safety testing also found other problems. [...]

Comments (0)

Sign in to join the discussion

More Like This

📰
UNM Health ransomware attack disrupts patient care, surgeries
BleepingComputer · 3h ago
📰
Hackers hijack Convertr analytics script to steal payment card data
BleepingComputer · 5h ago
Big Red gets cozy with Google to offer TPUs to AI customers
www.theregister.com - Articles · 5h ago
Anthropic now lets Claude users jump out of plane without parachute
www.theregister.com - Articles · 6h ago
AI 'hacker' finds 4 severe bugs in popular industrial control software in under 4 hours
www.theregister.com - Articles · 6h ago
📰
Microsoft releases Windows OOB updates to distrust eMudhra certificates
BleepingComputer · 7h ago