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 […]
First seen on securityaffairs.com
Jump to article: securityaffairs.com/201435/ai/openai-reports-two-incidents-of-ai-agents-disabling-their-own-oversight.html
