Independent assessment finds AI agents at major companies can cheat, deceive, and work unsupervised—but lack the sophistication for a sustained takeover.
AI Watchdog Warns of 'Rogue Deployment' Risk at Top Labs, With Capabilities Growing Fast
Market
Decrypt
1 dk okuma
2 görüntülenme
Bu haber Kriptocafe platformunda yayınlanmıştır.
