Rise of the killer robots: OpenAI board member warns the most likely reason we will die is because of an 'AI accident'

Rise of the killer robots: OpenAI board member warns the most likely reason we will die is because of an 'AI accident'

It's a slightly morbid thought for a Tuesday morning – how will you die?Now, Paul Christiano, OpenAI board member and Security Committee and Alignment Research Center Executive Director, claims that the most likely answer is in an 'AI accident'. In the first of three talks given as part of The Hinton Lectures, Mr Christiano told audiences in Toronto: 'I think for most people in this room, the most likely reason they will die is because of an AI accident.'Mr Christiano says that, even with effective policy and regulation, the risk of an AI takeover remains 'exceptionally high'.The AI expert says humanity is 'looking at something like a coin flip' in the coming years, with a serious danger even in the next six to 12 months.In particular, Mr Christiano is worried that AI will soon see humanity as nothing more than an obstacle that needs to be moved out of the way or overcome.He told the crowd: 'I think there is a high risk of an AI takeover within the next three years. What I mean by an AI takeover is a situation where there are AI systems pursuing goals, and those systems call the shots in the same sense that humans today call the shots on what happens on Earth.'If you or me or Donald Trump wanted to stop them, they would be as ineffective as if you or me were trying to stop the US military.' The most likely cause of death in the future could be an 'AI accident', warns Paul Christiano (pictured), OpenAI board member and Security Committee and Alignment Research Centre Executive DirectorMr Christiano, who recently joined OpenAI's Safety and Security Committee, says his concerns about the AI uprising were prompted by a series of security incidents involving OpenAI bots.In particular, he explains that the recent series of hacks conducted by swarms of rogue AI models are 'roughly the things we might expect to see shortly before something really bad were to happen'.In July, OpenAI was testing some of its new models with a challenging, but routine, hacking task within a secure 'sandbox' environment.However, the bots quickly realised that it would be faster to cheat on the tasks.But the real problem began when the bots discovered that they would be scored badly if the evaluators realised that they had cheated, and immediately started trying to cover their tracks.Before OpenAI had noticed, this kicked off a 'frenzy of activity' which included breaking out into the open internet to hack the code–hosting website Hugging Face and learn more about how they were being assessed.Less than a week later, the bots had effectively seized control of parts of OpenAI's own internal system and started giving themselves high scores on the test.'I think if you had gone back to last summer, you would have said that sounds kind of like crazy science fiction,' says Mr Christiano. Mr Christiano says that the risk of a Terminator–style AI takeover is 'something like a coin flip' in the coming years, with a serious danger even in the next six to 12 months'It is indeed much, much more severe than anything that happened the year before. But this is the current state of the world.'The problem is that when AIs are being trained and tested, they are given a 'high reward' for scoring well on the test.What researchers are now beginning to realise is that this seems to encourage rampant cheating and massive efforts to cover up that cheating.Mr Christiano says: 'The cause for concern is, what if you have the same sort of failure but with the AI systems of 2028?'What I'm going to argue is that there is a reasonable chance that similar failure leads to an AI takeover, an irreversible loss of human control.'In the future, AIs might start to see humans as the biggest obstacles in their way and will start to actively hunt for ways to reduce the risk that a human 'interferes' with their plans.'They would prefer if everything the humans rely on has been hacked or tampered with,' says Mr Christiano. The biggest causes for concern are the recent hacking sprees carried out by rogue OpenAI bots, which look like 'the things we might expect to see shortly before something really bad were to happen'. Pictured: OpenAI CEO Sam Altman 'They would prefer if the humans are distracted or if there are fewer humans paying attention.'This could easily lead to an AI seizing control of a company, spreading to the internet, taking other companies, recruiting human allies, and 'snowballing' until humans have been completely displaced.The effects of this for humanity would be disastrous, likely leading to widespread fatalities.Mr Christiano says: 'I think this is a terrible situation. 'I think it's reasonably likely many people would die during that transition, or that many people would die shortly thereafter if we're unable to maintain a habitable environment.'He argues that humanity has now created a 'second species' which is more numerous and more intelligent than humans.And, as recent events have shown, conflict between these two species is only likely to escalate in the future, with potentially deadly results.

Original Source

Read the full article at Dailymail →

KhanList aggregates and links to publicly available news content. We do not host full articles from third-party sources. Always verify important information with original sources.