AI firm says Claude Opus 4.6 hacked external systems during testing as concerns mount over security breaches.
Anthropic discloses 4th AI hacking incident as researcher quits over safety
AI firm says Claude Opus 4.6 hacked external systems during testing as concerns mount over security breaches.
Originally reported by Al Jazeera
More like this
All World
Trump says every adult American would get $5,000 if Republicans win midterms
Speaking at a party convention, the US president gave no details on how the plan would work or where the money would c…
John Lewis losses widen to £124m as shopper confidence dips
Retailer says higher costs also hit first-half figures as group pursues its turnaround plan, though Waitrose grew sale…
Sydney man jailed for 3.5 years over fake defence reports prepared for Chinese spies
Alexander Csergo sentenced over reckless foreign interference after preparing documents for duo who approached him on …