Elon Musk says AI has 'more 肯定的なs than 消極的なs' as he 開始する，打ち上げるs his own anti-woke 雑談（する） bot - in first public 外見 since 解雇する／砲火／射撃ing Don Lemon

• e-mail

AI doomster Elon Musk appears to have changed his tune on the 科学（工学）技術, （人命などを）奪う，主張するing the プロの／賛成のs of 前進するing the tech 最終的に outweigh the 反対／詐欺s.

Musk was speaking?公然と for the first time at an 人工的な 知能 首脳会議 Tuesday, a little いっそう少なく than a week after the 億万長者 解雇する／砲火／射撃d?Don Lemon.

The 無所属の政治家 tech mogul?― who 以前 called AI the 'most destructive 軍隊 in history' ― 持続するd there was still 'some chance that it will end humanity.' But his 発射／推定s were いっそう少なく 暗い／優うつな than usual.?

'I probably agree with Geof Hinton that it's about 10 パーセント or 20 パーセント,' Musk told 首脳会議 attendees, namechecking?Geoffrey Hinton, Google's?'Godfather of AI.'??

'But I think we are 長，率いるd for 豊富,' Musk opined, 'as the most likely 結果.'

'I think the probable 肯定的な シナリオ outweighs the 消極的な シナリオ,' he said.

The 明らかな トンing 負かす／撃墜する of Musk's 恐れるs about AI come as he 開始する，打ち上げるs his own 人工的な 知能 program 始める，決める to compete with ChatGPT 製造者 OpenAI: a 'sarcastic' AI dubbed Grok that's now in beta on Musk's rebrand of Twitter, X.?

AI doomster Elon Musk (above 中心) spoke at an 人工的な 知能 首脳会議 Tuesday, Abundance360, in conversation with the group's co-創立者 Peter Diamandis (権利). Musk told attendees 'the probable 肯定的な シナリオ' for AI 'outweighs the 消極的な シナリオ'

Hinton, 75, a British-Canadian AI 開拓する who?sensationally やめる his 職業 at Google last May?over his own 恐れるs and 悔いるs about AI, also spoke at this week's 首脳会議.

The event, Abundance360?by Singularity University, was created by futurist and X Prize 創立者 Peter Diamandis, who has 株d Musk's passion for the 私的な space race, boot-strapping a variety of start-ups 献身的な to micro-衛星s, space 観光旅行，事業 and even lunar rovers.

Diamandis interviewed Musk for Tuesday's live event 経由で a いつかs imperfect Starlink-link supported, X.com ビデオ livestream, as Musk sat on a 計画（する） bound for Los Angeles.

Geoffrey Hinton, 75?― a British-Canadian AI 開拓する who 問題／発行するd a 警告 that 'scary' chatbots like the popular ChatGPT could soon be smarter than humans?― also spoke at this week's Abundance360 首脳会議

Branded as the '広大な／多数の／重要な AI 審議,' this year's 見解／翻訳／版 of Diamandis' event spanned four days in?Palos Verdes, California. （衆議院の）議長's 含むd?Google futurist and coiner of the 称する，呼ぶ／期間／用語 'the Singularity,'?Ray Kurzweil, and?Trump-容赦d, 1980s 'junk 社債' financier?Michael Milken.

Former Google CEO?Eric Schmidt, who said last year that AI 提起する／ポーズをとるd an?'existential 危険' for humanity 'defined as many, many, many, many people 害（を与える）d or killed,' also took part in the 首脳会議.?

'It's called 'the singularity' for a 推論する／理由,' Musk quipped, 言及／関連ing Kurzweil's theory that a 未来 moment of exponential 科学技術の 進歩 will forever 合併する humanity with machines into a brilliant new 段階 of 進化.?

'When you have the advent of 人工的な superintelligence,' Musk continued, 'it is 現実に very difficult to 予報する what will happen next.'

But, he 追加するd: 'It's definitely going to happen ― and it's happening 急速な／放蕩な. So, I think really we just want to steer it in as 肯定的な a direction as possible.'?

The space-tech galvanizing, X Prize 創立者 Peter Diamandis (行う／開催する／段階 left)?interviewed Musk for Tuesday's live event 経由で a いつかs imperfect Starlink-link supported, X.com broadcast livestream, as Musk spoke while seated on a 計画（する） bound for Los Angeles

The 'godfather' of AI Geoffrey Hinton (中心 権利) 投げ上げる／ボディチェックするd a 手りゅう弾 into the 激怒（する）ing 審議 about the dangers of AI 科学（工学）技術 last May, after sensationally quitting his 職業 at Google. Tuesday, Musk said he agre ed with Hinton, while still 事業／計画（する）ing a more rosy 視野 on AI

READ MORE:?AI スキャンダル 激しく揺するs academia as nearly 200 熟考する／考慮するs are exposed as having been partly 生成するd by ChatGPT?

Scientists are submitting AI-written papers that 耐える telltale 調印するs of having been produced by ChatGPT: the phrase 'As of my last knowledge update.' Most of the articles are published in low-質 科学の 定期刊行物s that publish for a 料金. These いわゆる 'paper mills' are not new, but the 雪崩／（抗議などの）殺到 of AI-生成するd 科学の papers is - and it shows 調印するs of スピード違反 up.?

宣伝

Musk drew 終始一貫して from the realm of science fiction in a search for metaphors to better explain his 見通し on the 可能性のある 約束 and 落し穴s of 高度に 前進するd, 人工的な general 知能 (AGI) and other more 明確な／細部 forms of AI.

'I think we'll have an 結果 that's 類似の to the Ian Banks' "Culture" 調書をとる／予約するs,' Musk said from his airplane seat, calling the late Scottish 小説家 Banks' 一連の ten Culture novels かもしれない 'the best 想像するing of a 半分-utopian AI 未来.'

Banks' Culture novels take place in a 乳の Way 星雲 だいたい 9,000 years after humanity and other human-like 種類 have joined with AI to produce a '地位，任命する-scarcity' economy with little need for 法律s or 法律 施行.

Banks once 述べるd the utopian 見通し of his 調書をとる／予約するs as 'space 社会主義.'

Musk then pointed to the 殺し屋 robot HAL from Arthur C. Clarke.'s '2001: A Space 長期冒険旅行' as an example of how and why AI could become a 脅し to humanity.

The '核心 前提' of 2001, as Musk put it to the 首脳会議, was that 'things went wrong when they 軍隊d the AI to 嘘（をつく）.'?

'You kinda do grow an AGI,' Musk said.?

'It's almost like raising a kid, but a 最高の-genius, God-like 知能 kid ― and it 事柄s how you raise the kid, you know?'

In keeping with his past comments on the 問題／発行する, Musk 持続するd that the safest AI for humanity is one that is 'grown' to remain?'maximumly truth-捜し出すing and curious.'

'The best way to ac hieve AI safety is to just grow the AI, ーに関して／ーの点でs of the 創立／基礎 model and the 罰金-tuning, to be really truthful ― like don't 軍隊 it to 嘘（をつく）, even if the truth is unpleasant,' Musk said.

The 億万長者, who 購入（する）d the social マスコミ 場所／位置 Twitter in October 2022, then put in a plug for his 場所／位置, now called X, and its own AI chatbot in beta, Grok.?

Grok, Musk said to a wave of 賞賛 from the audience, will be 'maximally truthful' even if what it says is not '政治上 訂正する.'

?Grok, 'a humble AI assistant,' is only 利用できる to X 賞与金+ 加入者s.