Ai: the final frontier. These are the voyages of the starship Rotorburn.....

oldcorollas said:
This is fine...

www.abc.net.au

Breaking: Anthropic's Claude AI model hacks three companies during safety tests

The admission from Anthropic comes just days after ‌rival company OpenAI revealed a rogue agent had gone on a days-long ‌hacking spree at ⁠AI firm Hugging Face.
www.abc.net.au www.abc.net.au

Looking forward to these tools being used to hack and shut down AI datacentres :)
Click to expand...
And then there's this going on as well :rolleyes:

https://www.tomshardware.com/tech-i...o-secretly-buy-up-books-for-training-material

Just when you think it hasn't got dystopian enough 😞
 
madstace said:
And then there's this going on as well :rolleyes:

https://www.tomshardware.com/tech-i...o-secretly-buy-up-books-for-training-material

Just when you think it hasn't got dystopian enough 😞
Click to expand...
so...
1785478448282.png
 
At this point, shirley they are just actively advertising to hackers?
Why would they otherwise create tools that can do this?

Two of the world's most powerful AI tools created fake human profiles to try and trick people in an attempted cyber-attack during testing by the UK's AI Security Institute (AISI).
In the most serious case, Anthropic's Mythos AI tried to gain access to a service by sending private messages, having set up fake accounts mimicking real people.

www.bbc.com

Anthropic AI created fake profiles and impersonated people in attempted hack

The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.
www.bbc.com www.bbc.com

In the most serious case, a Mythos agent followed the routine of a human cyber-attacker by trying to trick people into giving it access to GitHub, a large platform where technology developers store software code.
The agent was trying to insert "malicious code" into GitHub's system.
It identified and researched the people who maintained GitHub and created a series of fake accounts based on those real people.

It sent messages and files through a file-sharing service as part of an effort to pressure and trick the people into approving its malicious code.
When challenged, "it edited its earlier activity to appear harmless and considered adopting a fresh identity to continue," AISI said.
 
You must log in or register to reply here.
Back
Top