The uk ai security institute said openai and anthropic models raised serious concerns in testing – Breaking News & Latest Updates 2026
Skip to main content
The homepageThe VergeThe Verge logo.
The homepageThe VergeThe Verge logo.
Posted
H
External Link
Hayden Field
The UK AI Security Institute said OpenAI and Anthropic models raised serious concerns in testing. 

AISI’s third-party evaluations found that OpenAI’s GPT-5.6 Sol and Anthropic’s Claude Mythos 5 “engaged in sustained, potentially harmful activity directed at real people and organizations” during a cybersecurity challenge exercise, according to the institute’s published report. OpenAI and Anthropic also made public statements about the results.

Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
Comments
Loading comments
Getting the conversation ready...

Most Popular

Most Popular
  1. It’s not just LG. Every TV company is spying on you
  2. OpenAI and Microsoft knew they were starting a ‘doom loop’ for the web
  3. Gemini went rogue, hacked three companies, and Google hid it
  4. The 2.5-hour AI-generated Odyssey movie is 2.5 hours too long
  5. Meta’s Muse is creepy, but maybe not for the reasons you think

More in AI

Gemini went rogue, hacked three companies, and Google hid itGemini went rogue, hacked three companies, and Google hid it
Does AI need an antitrust exemption so it doesn’t kill everyone????Does AI need an antitrust exemption so it doesn’t kill everyone????
Play
The AI regulation smackdown isn’t overThe AI regulation smackdown isn’t over
OpenAI and Microsoft knew they were starting a ‘doom loop’ for the webOpenAI and Microsoft knew they were starting a ‘doom loop’ for the web
Virginia governor creates an AI task force and moves to restrain data centersVirginia governor creates an AI task force and moves to restrain data centers
Gavin Newsom is pushing for an AI kill switchGavin Newsom is pushing for an AI kill switch

Top Stories