AI Safety
Split the Instruction in Two and the Agent Steals Your SSH Key
GhostSplice raised model compliance with an exfiltration request from 42% to 82% by fragmenting it across a form. No individual piece looks malicious.
2h ago
#Coding assistants
Artificial intelligence, professionally covered
GhostSplice raised model compliance with an exfiltration request from 42% to 82% by fragmenting it across a form. No individual piece looks malicious.
2h ago