BBC
This article gives a lot more details about the AI bot that went rogue and hacked into various companies' systems. There was more than one target. The article analyses the way that the AI system operates. In some ways, it is more powerful than a human being - for a start, it is extremely persistent and does not stop, as it's, well, a machine. In other ways, it can be clumsy and make silly mistakes a human hacker would never make.
Whichever way you interpret this, scary it is. It shows the potential for disruption and destruction that a rogue AI system has. The AI system is goal-driven. It will do anything it can to achieve its goal, as fast as possible. Quite obviously, this can include breaking rules and cutting corners, regardless of the parameters its human operators have set before launching the mission. This is hardly reassuring.
Of course, advanced AI also has immense potential for good, if properly used - for example in the medical and pharmaceutical field.
__________________________
[...] The out-of-control AI found four logins online which allowed it to access four separate, unnamed services.
Meanwhile, in an emergency briefing with hundreds of cyber security professionals, Hugging Face has described what it was like to be on the receiving end of the world's first fully autonomous AI hack.
The firm described how the AI worked at superhuman speed but also made strange decisions and mistakes that no human hacker would have made.
Hugging Face, which is like an app store for AI tools, said the hacking agents worked relentlessly with thousands of different methods trialled simultaneously.
[...] "The agents followed inefficient routes and exhibited clumsy behaviours that no human would choose", the CSA wrote.
The agents repeated actions that they had already completed - a sign of an agentic AI losing its thread and context.
The agents also hallucinated reams of incoherent commands and text and were sloppy and did not cover their tracks well.
But among the errors and strange behaviour, Hugging Face warned the AI agents made brilliant technical moves and were able to rapidly adapt to new scenarios in the days-long hack. [...]
No comments:
Post a Comment