OpenAI's GPT-6.1 Terra is safer overall, but shows more destructive-action flags in tests
· bleepingcomputer.com · popularity 21/100 · 0 similar stories today
Read the original at bleepingcomputer.com →
Summary
OpenAI confirmed GPT-6.1 Terra is safer overall than some of its older models, but its safety testing also found other problems. [...]
Found in: BleepingComputer. Rating basis: single outlet; outlet tier 2 (unlisted); 1 feeds; feed position 2.