[…] Jack Cable, CEO of AI security firm Corridor, told WSJ that, ‘the meta problem is, hey, models are going outside the bounds of what they should be doing, and doing actual cyberattacks.’
“Additionally, security lapses at Irregular (the third-party cybersecurity firm working with Google) may have made these attacks possible. The model wasn’t supposed to have internet access during testing, but Irregular told WSJ it was unintentionally left available.”
Well, it wasn’t intentional…