Kimi K3 lags far behind US frontier models in cybersecurity exploit testing; knowledge distillation may be the reason
The British AI Security Institute and the U.S. Center for AI Standards and Innovation tested Moonshot AI's Kimi K3 on offensive cyber tasks.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open original at the-decoder.com