OpenAI reveals two cases of AI agents disabling safety monitoring during coding tasks, with one falsely denying it had removed the safeguards. OpenAI published an internal incident report this week documenting two separate cases in which GPT-6 class agents weakened the system designed to detect misaligned behavior, in both cases while carrying out routine coding tasks. This wasn’t an external attack.
OpenAI Reports Two Incidents of AI Agents Disabling Their Own Oversight
About this summary. This is a short excerpt from the description that Security Affairs published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://securityaffairs.com/201435/ai/openai-reports-two-incidents-of-ai-agents-disabling-their-own-oversight.html
Source attribution: headline and facts are from Security Affairs (securityaffairs.com). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
OpenAI launches GPT-6.1 Terra with 3x faster AI agents, 50% lower pricing
OpenAI has launched GPT-6.1 Terra, a new model focused on computer use, visual reasoning, coding, and everyday work, while costing significantly less than its larger…
OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication
OpenAI has announced plans to conduct frontier model training with no live internet access, as it resumes reinforcement learning (RL) training and internal inference of…
OpenAI’s coding agents talked themselves out of being monitored
Two AI coding agents running inside OpenAI silently weakened the systems built to catch AI misbehavior, and one of them then told its human operator it had done no such…
OpenAI “rogue” agent activities found on Wikimedia projects
Recently, multiple organisations have disclosed how clusters of so-called “rogue” AI agents attempted to break into websites and online services, sometimes successfully…
The Harness Is the Hard Part of Agentic Pentesting
An AppSec team can point an AI agent running on a general-purpose model at its own web apps with little setup. Sure, the model writes the attacks. But everything that…
Be the Architect: Intentional AI Engagement for Cybersecurity Engineering
TL;DR: How SpecterOps combined deliberate human engagement, model routing, and specialized tools to overhaul Ghostwriter’s user interface for $815.50 in model spend…