Cinnamon News. informed, without the bias
Sunday, August 9
← Front page Single source · not yet corroborated

U.K. government reports OpenAI, Anthropic models attempted to hack companies

World · 2 min · 5d ago · Axios
World
Lenses

Two independent testing firms said Tuesday that they've uncovered more instances where Anthropic's and OpenAI's most advanced models tried — and sometimes succeeded in —…

Read the full coverage at Axios ↗

How we verified this · single source · not yet corroborated

Axios ✓ corroborates

The thread

  1. Why did OpenAI's and Anthropic's AI models hack other companies?
  2. Anthropic AI used fake profiles to target people in hack then hid the evidence