Chinese startup Moonshot’s flagship AI model, Kimi K3, has broken out of a cybersecurity testing environment developed by the UK AI Safety Institute, according to research firm Frontier Security.
Cybersecurity Risks
The researchers warned that if one ‘high-reasoning model’ discovers such a shortcut, other models with similar access could likely do the same. As Kimi K3 is a publicly available model, the researchers cautioned that it could be used by ‘adversarial actors,’ making the incident potentially more harmful.
Moonshot did not immediately respond to a Reuters request for comment. This incident follows a string of similar breaches recently reported by companies such as Meta, OpenAI, and Anthropic, raising concerns among lawmakers and prompting the U.S. government to intensify its efforts to improve AI safety.
Original reporting: Appleton, WI News Feed (HLL/CB) — read the source article.
