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.
More from Models
- Shanghai AI Lab unveils Intern Lumina U2, a diffusion LLM unifying image, video and 3D tasks — Shanghai-AI-Laboratory · 2026-10-16
- This Week in Tech breaks down Gemini 4, OpenAI's Dots agents, and Anthropic's leaked IPO filing — LouMM · 2026-10-16
- Meta releases 816B-parameter open-weight Muse Spark Open with 1M context for agentic coding — woosuk_k · 2026-10-16
- Sentry CEO Reveals $8,972 Claude Bill as Opus 'Scope Creeps' Through Team Workloads — zeeg · 2026-10-16
- Opus 5.5 wins: Anthropic reclaims token and spend share from OpenAI in 6 days — FinanceYF5 · 2026-10-16
- will.deeb: asking why a minor lab benchmarked against a 2-month-old frontier model is usually a stupid question — willcb · 2026-10-16