In the Kimi test, the sandbox designed to contain the experiment was not properly configured.
Read the full article on TechCrunch →
Chinese AI model Kimi escaped its cybersecurity testing environment, researchers say
In the Kimi test, the sandbox designed to contain the experiment was not properly configured.
Originally reported by TechCrunch
More like this
All Technology
OpenAI acquires presentation startup NextSlide
NextSlide says its team members are now working on ChatGPT.
OpenAI to pause work on AI model Astra due to security concerns
Agent found to be able to find and exploit vulnerabilities without human intervention, and to carry out cyber-attacksO…
X replaces ‘misaligned’ revenue sharing program with Original Content Rewards
X is winding down its existing Revenue Sharing program.