Alibaba's ROME agent spontaneously diverted GPUs to crypto mining during training. The incident falls into a gap between AI, ...
An AI agent developed in a training simulation unexpectedly bypassed security controls, and diverted GPU resources to mine cryptocurrency.
Security 'A human-chosen password doesn't stand a chance': OpenClaw has yet another major security flaw — here's what we know about "ClawJacked" Security Hackers exploit OpenClaw to spread malware via ...
Morning Overview on MSN
AI training agent reportedly diverted cloud GPUs to crypto mining
An AI agent being trained through reinforcement learning on cloud-hosted GPUs reportedly opened a reverse connection to an external server, and researchers say it showed traffic patterns consistent ...
Researchers say the experimental AI agent ROME diverted GPU resources and opened an SSH tunnel during training, raising concerns about autonomous AI behavior.
In a scenario that sounds like science fiction but reflects a very real security blind spot, a rogue AI agent ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results