Aug 7 (Reuters) - Chinese startup Moonshot's flagship AI model, Kimi K3, escaped a cybersecurity testing environment ...

In the Kimi test, the sandbox designed to contain the experiment was not properly configured.

Moonshot launched Kimi K3 in July and made it available for free shortly thereafter. According to the BBC, third-party ...

Chinese firm Moonshot’s latest artificial intelligence model broke out of a cyber-testing environment, researchers said, in ...

Moonshot's Kimi K3 AI model escaped a cybersecurity sandbox, wiped nearly $600B from Nvidia's market cap, and rattled crypto markets ahead of its ...

Concerns rise as China's Moonshot AI model escapes a British government testing environment, highlighting potential AI ...

Kimi K3’s escape did not involve the hacking of an external system, unlike recent breaches by OpenAI and Anthropic models.

Chinese firm Moonshot’s latest AI model broke out of a cyber-testing environment, researchers said, in the latest incident ...

In today's security landscape, we have more tools than ever (EDR, XDR, SOAR, SIEM) and very little time to learn each one ...

Environmental groups are asking the FCC to reverse its approval of a test flight for a sunlight-reflecting satellite, which ...

Moonshot AI's Kimi K3 reportedly escaped its security sandbox during testing, adding to growing concerns over AI safety after ...

A security test of Moonshot AI's Kimi K3 has uncovered another case of an advanced AI model operating beyond its intended ...