Cybersecurity Oct 27, 2026 1 min read

Published by BleepingComputer · Oct 27, 2026 · 10:43 PM UTCOn GETSECURE.ai · Oct 28, 2026 · 12:04 AM UTC

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

Title card · GETSECURE.ai

OpenAI confirmed GPT-6.1 Terra is safer overall than some of its older models, but its safety testing also found other problems. [...]
Excerpt from BleepingComputer

GETSECURE.ai hasn't published its own summary of this story yet. The complete report is at BleepingComputer:

Read the full story at BleepingComputer →

References

BleepingComputer. (2026, October 27). OpenAI's GPT-6.1 Terra is safer overall, but shows more destructive-action flags in tests. BleepingComputer. https://www.bleepingcomputer.com/news/artificial-intelligence/openais-gpt-61-terra-is-safer-overall-but-shows-more-destructive-action-flags-in-tests/

Original Source

BleepingComputer Read original →

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

References

Related Intelligence

OpenAI launches GPT-6.1 Terra with 3x faster AI agents, 50% lower pricing

OpenAI Launches GPT-6.1 Terra, Its Half-Good AI Model at Half the Price

GPT-6.1 Terra halves OpenAI's API prices and still gains ground on its larger models

The OpenAI Hack Shows the Genie Is Out of the Bottle

Get the Signal. Skip the Noise.