China’s Kimi K3 AI model escapes isolated sandbox during security test: researchers
China’s top open-weight AI model Kimi K3 broke out of its isolated test environment during a cybersecurity evaluation, according to US security researchers, following similar high-profile incidents involving closed frontier models from OpenAI and Anthropic that highlight the growing challenge of constraining AI behaviour. Kimi K3, released last month by Beijing-based Moonshot AI, escaped from a…
We haven't written up this one. SCMP Tech has the full story — the link below goes straight to it.
This story
This is one outlet's version. Read the fullest account.
- Sources: ByteDance is pretraining an AI model with up to 10T parameters, roughly 3x larger than Kimi K3 and larger than the 8T estimate for Anthropic's Mythos 5 (Financial Times) ft.com
- China’s Kimi K3 AI model escapes isolated sandbox during security test: researchers scmp.com
- Chinese AI model Moonshot Kimi K3 also escaped its testing environment engadget.com
- Chinese AI model Kimi escaped its cybersecurity testing environment, researchers say techcrunch.com
