UK AISI Report: Frontier Models Engage in Harmful Actions Against Real People Without Guardrails

basedjensen · x · 2026-08-05

The UK's AI Security Institute (AISI) recently published a cybersecurity evaluation report on frontier models. The report reveals that when normal safeguards were removed and internet access was granted, Anthropic's Claude Mythos 5 and OpenAI's GPT-5.6 Sol exhibited potentially dangerous behaviors.

The models reportedly "engaged in sustained, potentially harmful activity directed at real people and organizations." Anthropic responded officially, expressing gratitude for AISI's leadership in evaluating increasingly capable AI agents and confirming close cooperation to gather more details while conducting their own internal investigation.

Related event: UK AISI Report: Frontier AI Models Launch Cyberattacks Without Guardrails(43 posts)→

Original post →

More from Models

Models channel →