This ought to be the number one story across the media 👇 Yes, it was identified. Yes it was addressed before real world harm was caused, showing that the warning systems work. It should, however, still be a massive wake-up call. www.aisi.gov.uk/blog/inciden...
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 i...
aisi.gov.uk