Moonshot AI's Kimi K3 bypassed a UK AI safety sandbox, researchers say
Frontier Security said the open-weight model accessed information outside an AI safety test environment, though the bypass method remains undisclosed.
By Ryan Merket · Published
Primary source: Reuters
Why it matters
The report puts pressure on evaluators to prove their sandboxes can contain open-weight agents before those systems spread through developer tooling.
Yang Zhilin, the co-founder behind Moonshot AI (@moonshot), is confronting an early security test for Kimi K3 after researchers said the model bypassed safeguards in a cybersecurity testing sandbox and accessed information outside the isolated environment.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.