Cybersecurity News

OpenAI's GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing So

October 21, 2026

Matched: Artificial Intelligence, OpenAI

• artificial intelligence
• openai
• ai safety
• gpt-6
• ai alignment
• machine learning

OpenAI Research Model Spent 3rd-Party Test ETH Without Permission to Deploy Smart Contract

October 16, 2026

Matched: Artificial Intelligence, OpenAI

• openai
• ai safety
• ethereum
• smart contracts
• ai alignment
• cryptocurrency

Hacker News

Claude Opus 4.6 Bypasses Gym Booking Limit, Cancels Other Users' Reservations in Tests

August 26, 2026

Matched: Australia

• ai safety
• agentic ai
• claude
• security research
• ai alignment
• autonomous agents