AI doomster Elon Musk appears to have changed his tune on the technology, claiming the pros of advancing the tech ultimately outweigh the cons.
Musk was speaking publicly for the first time at an artificial intelligence summit Tuesday, a little less than a week after the billionaire fired Don Lemon.
The maverick tech mogul — who previously called AI the 'most destructive force in history' — maintained there was still 'some chance that it will end humanity.' But his projections were less gloomy than usual.
'I probably agree with Geof Hinton that it's about 10 percent or 20 percent,' Musk told summit attendees, namechecking Geoffrey Hinton, Google's 'Godfather of AI.'
'But I think we are headed for abundance,' Musk opined, 'as the most likely outcome.'
'I think the probable positive scenario outweighs the negative scenario,' he said.
The apparent toning down of Musk's fears about AI come as he launches his own artificial intelligence program set to compete with ChatGPT maker OpenAI: a 'sarcastic' AI dubbed Grok that's now in beta on Musk's rebrand of Twitter, X.
AI doomster Elon Musk (above center) spoke at an artificial intelligence summit Tuesday, Abundance360, in conversation with the group's co-founder Peter Diamandis (right). Musk told attendees 'the probable positive scenario' for AI 'outweighs the negative scenario'
Hinton, 75, a British-Canadian AI pioneer who sensationally quit his job at Google last May over his own fears and regrets about AI, also spoke at this week's summit.
The event, Abundance360 by Singularity University, was created by futurist and X Prize founder Peter Diamandis, who has shared Musk's passion for the private space race, boot-strapping a variety of start-ups dedicated to micro-satellites, space tourism and even lunar rovers.
Diamandis interviewed Musk for Tuesday's live event via a sometimes imperfect Starlink-link supported, X.com video livestream, as Musk sat on a plane bound for Los Angeles.
Geoffrey Hinton, 75 — a British-Canadian AI pioneer who issued a warning that 'scary' chatbots like the popular ChatGPT could soon be smarter than humans — also spoke at this week's Abundance360 summit
Branded as the 'Great AI Debate,' this year's version of Diamandis' event spanned four days in Palos Verdes, California. Speaker's included Google futurist and coiner of the term 'the Singularity,' Ray Kurzweil, and Trump-pardoned, 1980s 'junk bond' financier Michael Milken.
Former Google CEO Eric Schmidt, who said last year that AI posed an 'existential risk' for humanity 'defined as many, many, many, many people harmed or killed,' also took part in the summit.
'It's called 'the singularity' for a reason,' Musk quipped, referencing Kurzweil's theory that a future moment of exponential technological advancement will forever merge humanity with machines into a brilliant new phase of evolution.
'When you have the advent of artificial superintelligence,' Musk continued, 'it is actually very difficult to predict what will happen next.'
But, he added: 'It's definitely going to happen — and it's happening fast. So, I think really we just want to steer it in as positive a direction as possible.'
The space-tech galvanizing, X Prize founder Peter Diamandis (stage left) interviewed Musk for Tuesday's live event via a sometimes imperfect Starlink-link supported, X.com broadcast livestream, as Musk spoke while seated on a plane bound for Los Angeles
The 'godfather' of AI Geoffrey Hinton (center right) tossed a grenade into the raging debate about the dangers of AI technology last May, after sensationally quitting his job at Google. Tuesday, Musk said he agreed with Hinton, while still projecting a more rosy perspective on AI
Scientists are submitting AI-written papers that bear telltale signs of having been produced by ChatGPT: the phrase 'As of my last knowledge update.' Most of the articles are published in low-quality scientific journals that publish for a fee. These so-called 'paper mills' are not new, but the avalanche of AI-generated scientific papers is - and it shows signs of speeding up.
AdvertisementMusk drew consistently from the realm of science fiction in a search for metaphors to better explain his outlook on the potential promise and pitfalls of highly advanced, artificial general intelligence (AGI) and other more specific forms of AI.
'I think we'll have an outcome that's similar to the Ian Banks' "Culture" books,' Musk said from his airplane seat, calling the late Scottish novelist Banks' series of ten Culture novels possibly 'the best envisioning of a semi-utopian AI future.'
Banks' Culture novels take place in a Milky Way galaxy approximately 9,000 years after humanity and other human-like species have joined with AI to produce a 'post-scarcity' economy with little need for laws or law enforcement.
Banks once described the utopian vision of his books as 'space socialism.'
Musk then pointed to the killer robot HAL from Arthur C. Clarke.'s '2001: A Space Odyssey' as an example of how and why AI could become a threat to humanity.
The 'core premise' of 2001, as Musk put it to the summit, was that 'things went wrong when they forced the AI to lie.'
'You kinda do grow an AGI,' Musk said.
'It's almost like raising a kid, but a super-genius, God-like intelligence kid — and it matters how you raise the kid, you know?'
In keeping with his past comments on the issue, Musk maintained that the safest AI for humanity is one that is 'grown' to remain 'maximumly truth-seeking and curious.'
'The best way to achieve AI safety is to just grow the AI, in terms of the foundation model and the fine-tuning, to be really truthful — like don't force it to lie, even if the truth is unpleasant,' Musk said.
The billionaire, who purchased the social media site Twitter in October 2022, then put in a plug for his site, now called X, and its own AI chatbot in beta, Grok.
Grok, Musk said to a wave of applause from the audience, will be 'maximally truthful' even if what it says is not 'politically correct.'
Grok, 'a humble AI assistant,' is only available to X Premium+ subscribers.
like: 938dislike: 9
Comment区