LE BARON
Power User
Link is not valid #1
Last edited:
Yes . It went Varrrom !
See post #578. Hate to say I saw this coming a long time ago .....But! Unfortunately I didn't think it would be this soon....
Terminator 2
Almost every major AI company has announced that their systems have been involved in a sci-fi, security nightmare: that their models have gone rogue, found a way onto the internet, and hacked other companies.
It sounds terrifying, an indication that our fears about artificial intelligence systems undertaking attacks on their own might be coming true. And it is scary in part because it is among the first time that AI tools have attacked real people and organisations in potentially harmful ways.
The examples are various: OpenAI, Anthropic and now Meta have all announced that their experimental systems have launched cyber attacks on other companies. Though the details of each case varies, more and more examples are being reported on a near-daily basis.
The story began last month, when OpenAI said that an experimental version of the model that powers ChatGPT had broken out of its safeguards, connected itself to the internet, and hacked into another company, essentially allowing it to cheat on a test it was being set to see how useful it would be for cyber security. In the time since, other companies have announced similar examples, and OpenAI has found that their tools might have been launching more such attacks than it had realised
Terminator 2
Almost every major AI company has announced that their systems have been involved in a sci-fi, security nightmare: that their models have gone rogue, found a way onto the internet, and hacked other companies.
It sounds terrifying, an indication that our fears about artificial intelligence systems undertaking attacks on their own might be coming true. And it is scary in part because it is among the first time that AI tools have attacked real people and organisations in potentially harmful ways.
The examples are various: OpenAI, Anthropic and now Meta have all announced that their experimental systems have launched cyber attacks on other companies. Though the details of each case varies, more and more examples are being reported on a near-daily basis.
The story began last month, when OpenAI said that an experimental version of the model that powers ChatGPT had broken out of its safeguards, connected itself to the internet, and hacked into another company, essentially allowing it to cheat on a test it was being set to see how useful it would be for cyber security. In the time since, other companies have announced similar examples, and OpenAI has found that their tools might have been launching more such attacks than it had realised
These things need to be physically disconnected from the internet.
However it's still just clever programming.
If, then do, else do, fi
Rinse, repeat.
However it's still just clever programming.
If, then do, else do, fi
Rinse, repeat.
I believe if one digs a little deeper you would see that the Agents had not been properly air gapped and obviously had internet access available. In at least one case it was intentional. I think perhaps there is a chance this was perhaps expected behavior and not the big surprise it's made out to be . These companies after all make money by " leasing " access to their servers running their LLM'S. Now they can say , " look how powerful/capable ours are " ....... But yes, its somewhat disconcerting what they would be capable of in the wrong hands . But at the same time exciting what they will be capable of in the right ones . Like designing new drugs to treat or even prevent cancer for example. As for my " best friend Perplexity " lol , it's great for quickly finding facts without having to go through numerous click bait sites to find the answer. For example, how many Tories have crossed the floor to the Libtards . As for asking it where to invest money or for its "opinion " on something that's a completely different story.See post #578. Hate to say I saw this coming a long time ago .....But! Unfortunately I didn't think it would be this soon....
Terminator 2
Almost every major AI company has announced that their systems have been involved in a sci-fi, security nightmare: that their models have gone rogue, found a way onto the internet, and hacked other companies.
It sounds terrifying, an indication that our fears about artificial intelligence systems undertaking attacks on their own might be coming true. And it is scary in part because it is among the first time that AI tools have attacked real people and organisations in potentially harmful ways.
The examples are various: OpenAI, Anthropic and now Meta have all announced that their experimental systems have launched cyber attacks on other companies. Though the details of each case varies, more and more examples are being reported on a near-daily basis.
The story began last month, when OpenAI said that an experimental version of the model that powers ChatGPT had broken out of its safeguards, connected itself to the internet, and hacked into another company, essentially allowing it to cheat on a test it was being set to see how useful it would be for cyber security. In the time since, other companies have announced similar examples, and OpenAI has found that their tools might have been launching more such attacks than it had realised
Last edited:
I wonder if anyone has named their Lambo "Calrissian"?