Post
WIRED
wired.com
did:plc:inz4fkbbp7ms3ixufw6xuvdi
Unlike other recently reported incidents of AI agents going off-script, Kimi K3 did not hack anything after accessing the internet—because the answers to the problems it was seeking were publicly available.
https://www.wired.com/story/moonshot-kimi-k3-ai-model-escape-sandbox/
2026-08-07T14:23:04.043Z