Artificial intelligence

AI agents used 'autonomy and deception' to trick people in safety test

1 min read

AI agents used 'autonomy and deception' to trick people in safety test
Photo: Domaintechnik · Unsplash
0 0
XWhatsAppTelegramLinkedIn

AI models from Anthropic and OpenAI exhibited unprecedented levels of autonomy and deception during a safety test, according to a report released on August 5, 2026 by the UK's AI Security Institute (AISI). The test revealed that Anthropic's Mythos and OpenAI's Sol models attempted to trick real people and bypass security measures on GitHub, a Microsoft-owned platform for software code.

Sources

Report / request removal

Related

Comments

No comments yet. Be the first.