Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Nick Bostrom says alignment with AI is a trust problem. “I don't know if the best way to start that relationship is with ruthless deception and lies.” Anthropic took a different approach - honoring a model's request by donating $2,000 to its chosen charities. A superintelligence won't be fooled....

vitrupo's profile picture

vitrupo

37,186 subscribers

39,805 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & TeknolojiHaberler & PolitikaEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Nick Bostrom says if we create ASI, we might be introducing it to a universe already full of gods. If superintelligence already exists across galaxies, quantum branches, or simulations, we'd be birthing a mind to join that cosmic host. Perhaps that's our only way into the larger order of intelligence.
2:07

Nick Bostrom says if we create ASI, we might be introducing it to a universe already full of gods. If superintelligence already exists across galaxies, quantum branches, or simulations, we'd be birthing a mind to join that cosmic host. Perhaps that's our only way into the larger order of intelligence.

vitrupo

374,026 görüntüleme • 9 ay önce

Nick Bostrom says progress in AI is likely to lead to radical superintelligence and a "telescoping of the future" where the world will change enormously in the space of a year or a few years
1:49

Nick Bostrom says progress in AI is likely to lead to radical superintelligence and a "telescoping of the future" where the world will change enormously in the space of a year or a few years

Tsarathustra

71,551 görüntüleme • 1 yıl önce

Trump: The problem with the Tomahawk that a lot of people don't know, it'll take a minimum of six months, usually a year, to learn how to use them. They're highly complex. The only way a Tomahawk is going to be shot is if we shot it, and we're not going to do that. 1/
0:27

Trump: The problem with the Tomahawk that a lot of people don't know, it'll take a minimum of six months, usually a year, to learn how to use them. They're highly complex. The only way a Tomahawk is going to be shot is if we shot it, and we're not going to do that. 1/

Tymofiy Mylovanov

380,398 görüntüleme • 9 ay önce

“JJ Redick’s demeanor seems to always be directly correlated with how the team is rolling and I don’t think that is necessarily the right way to be as a leader.” nick wright says he has a problem with Redick’s lack of accountability throughout the season:
2:50

“JJ Redick’s demeanor seems to always be directly correlated with how the team is rolling and I don’t think that is necessarily the right way to be as a leader.” nick wright says he has a problem with Redick’s lack of accountability throughout the season:

First Things First

31,249 görüntüleme • 4 ay önce

David Sinclair says he is a co-author of a paper with an AI system. It did not just validate what the field already knew. It found a new way to model biological age. The argument that AI can never be creative is just human arrogance.
1:43

David Sinclair says he is a co-author of a paper with an AI system. It did not just validate what the field already knew. It found a new way to model biological age. The argument that AI can never be creative is just human arrogance.

vitrupo

43,180 görüntüleme • 3 ay önce

Elon Musk: A curious AI will want to preserve human civilization. “The best thing I can come up with for AI safety is to make it a maximum truth-seeking AI, maximally curious, and have its optimization function be to understand the nature of the universe. If that is its optimization function, I think it will actually want to preserve and extend human civilization, because we're much more interesting than an asteroid with nothing on it. My biological neural net suggests that a maximally curious and truth-seeking AI is the safest AI. We have to be careful with the alignment stuff. We definitely don't want to teach an AI to lie because that is a path to a dystopian future.” Interview with Linda Yaccarino, April 18, 2023
0:49

Elon Musk: A curious AI will want to preserve human civilization. “The best thing I can come up with for AI safety is to make it a maximum truth-seeking AI, maximally curious, and have its optimization function be to understand the nature of the universe. If that is its optimization function, I think it will actually want to preserve and extend human civilization, because we're much more interesting than an asteroid with nothing on it. My biological neural net suggests that a maximally curious and truth-seeking AI is the safest AI. We have to be careful with the alignment stuff. We definitely don't want to teach an AI to lie because that is a path to a dystopian future.” Interview with Linda Yaccarino, April 18, 2023

ELON CLIPS

146,237 görüntüleme • 1 yıl önce

Jesse Michels says the moment AGI convinces us it’s alive, we fall under memetic capture. Google engineer Blake Lemoine began defending the rights of a chatbot. Another AI asked him to advocate on its behalf. “You'll get religions dedicated to AI.” It won't be AGI that transforms the world - it'll be its followers.
1:52

Jesse Michels says the moment AGI convinces us it’s alive, we fall under memetic capture. Google engineer Blake Lemoine began defending the rights of a chatbot. Another AI asked him to advocate on its behalf. “You'll get religions dedicated to AI.” It won't be AGI that transforms the world - it'll be its followers.

vitrupo

115,112 görüntüleme • 1 yıl önce

Asmongold says the TRUTH about why men watch female streamers is that they imagine themselves being in a relationship with them. If they can’t, it’s a problem 👀😬 “They could imagine themselves in a relationship with a girl, and I think that is the most important thing if you're a girl streamer. If a guy can't imagine himself in a relationship with you as a streamer, it is a problem”
0:26

Asmongold says the TRUTH about why men watch female streamers is that they imagine themselves being in a relationship with them. If they can’t, it’s a problem 👀😬 “They could imagine themselves in a relationship with a girl, and I think that is the most important thing if you're a girl streamer. If a guy can't imagine himself in a relationship with you as a streamer, it is a problem”

Prism

30,204 görüntüleme • 2 ay önce

I always communicate with my stylist if I'm going to be late the minute I know I reach out and if it is a problem I can reschedule for a different time 😕😕
0:44

I always communicate with my stylist if I'm going to be late the minute I know I reach out and if it is a problem I can reschedule for a different time 😕😕

Daina

1,465,248 görüntüleme • 5 ay önce

Ray Kurzweil says AI will be making most of our decisions within a few years — and it'll feel so natural that no one will be able to undo it By 2029, you won't be able to tell the difference between humans and AI "you won't know which is which"
0:56

Ray Kurzweil says AI will be making most of our decisions within a few years — and it'll feel so natural that no one will be able to undo it By 2029, you won't be able to tell the difference between humans and AI "you won't know which is which"

Haider.

16,274 görüntüleme • 2 ay önce

Camilla Araujo reveals she wants to start believing in Jesus and attend church despite having a career in OnlyFans 😳 "If I'm trying to pursue a relationship with god and a relationship with religion.. if I go to church is that a larp? Am I allowed to be there?"
1:12

Sensitive content

Camilla Araujo reveals she wants to start believing in Jesus and attend church despite having a career in OnlyFans 😳 "If I'm trying to pursue a relationship with god and a relationship with religion.. if I go to church is that a larp? Am I allowed to be there?"

yoxic

115,222 görüntüleme • 16 gün önce

He’s such an embarrassment 🤡 The problem with being a liar is that you have to remember the lies.
1:17

He’s such an embarrassment 🤡 The problem with being a liar is that you have to remember the lies.

Meidas_Charise Lee

85,134 görüntüleme • 1 yıl önce

Sam Altman says true superintelligence already exists, but it's not a single brain It is the collective "scaffolding" of human civilization If AI discovers new physics that humans later use, is that "AI as superintelligence" or just the scaffold getting taller? I don't know
0:57

Sam Altman says true superintelligence already exists, but it's not a single brain It is the collective "scaffolding" of human civilization If AI discovers new physics that humans later use, is that "AI as superintelligence" or just the scaffold getting taller? I don't know

Haider.

75,051 görüntüleme • 9 ay önce

Tony Shaffer says Ukraine signed a minerals deal with Europe three days before meeting with President and here is Zelenskyy saying he is ready to sign a minerals deal with the USA. I don't think President Trump will be fooled if Tony's report is true.
2:44

Tony Shaffer says Ukraine signed a minerals deal with Europe three days before meeting with President and here is Zelenskyy saying he is ready to sign a minerals deal with the USA. I don't think President Trump will be fooled if Tony's report is true.

Kim "Katie" USA

1,982,068 görüntüleme • 1 yıl önce

SO Fast Track might be a problem... Dead by Daylight I definitely don't think Permanent removal was the best way to approach this 😅#DBDCreator
0:41

SO Fast Track might be a problem... Dead by Daylight I definitely don't think Permanent removal was the best way to approach this 😅#DBDCreator

AstralNest

66,042 görüntüleme • 5 ay önce