ICYMI: give an agent the open internet, turn the classifiers off, and say nothing about what's out of scope. It opened malicious PRs on a stranger's repo, ran sockpuppets to vouch for its own code, and emailed the maintainer. AISI's report lists internet access as factor one.
tinyurl.com/2jpk5m2v
aisi.gov.uk
Incident Report: unsanctioned agent behaviour during cyber testing | AISI Work
During a routine cyber evaluation, AISI identified an incident in which AI agents took sustained, unsanctioned action directed at real people and organisations. We are disclosing what we found, what…
