Topic: Articial Intelligence

[patentlymn]

She says this is a bot of her. Not sure if she is real or not. There is a real person. Not sure what is on the YT video.

https://youtu.be/86GV5zhNA4g
The Next 3 Years of AI: Why Even Experts Are Terrified
Julia McCoy

https://youtu.be/2Ev2FKAHuTc
Ilya Sutskever Breaks Silence: The Wild Truth About AI's Future | OpenAI's Ex-Chief Scientist

Key revelations from this talk:

-Why we've hit "peak data" and what this means for AI development
-How future AI will be radically different from today's systems
-Why superintelligent AI will be unpredictable in ways we can't imagine
-The surprising connection between human evolution and AI development
-Why current AI is just scratching the surface of true reasoning capabilities

Sutskever, who left OpenAI this year to start Safe Superintelligence Inc., presented a vision of AI that goes far beyond current capabilities.

He talks about how we're approaching a fundamental shift in how AI systems work, moving from pattern matching to true reasoning and agency.

This video breaks down his most important insights and what they mean for the future of artificial intelligence. Whether you're an AI researcher, tech enthusiast, or just curious about where technology is headed, this is a must-watch exploration of what's coming next in AI.

Full talk given by Ilya Sutskever in Vancouver on Friday, December 13, at the Conference on Neural Information Processing Systems (NeurIPS).

[patentlymn]

Chat GPT
No, she wasn't kidding. Julia McCoy has mentioned that some of her YouTube videos feature an AI-generated avatar reading her real words. This means that while the content comes from her, the voice and visuals are AI-generated. This is becoming more common in content marketing, where AI can be used to create realistic video representations of real people without them having to record every piece of content themselves.

[patentlymn]

So some guy used open AI AI "deep research" model to learn what cancer treatments for his wife. Better than professional advice. The video at start is a "digital avatar" of the real person. She returns at 24 min after the long tech talk.

https://youtu.be/2Y701bcVsMw

[Libertas]

Next leap for AI is expected to be in healthcare...lots of applications there, perhaps that is a "good" development and can help drive down costs and advance cures...guess we'll find out...

Then there's the dark side...

In a strange way, the timing of this research publication release aligns with my current concerns about DOGE revelations within the USA about the USAID and CIA activity.

In short, I worry the “old system of control” mechanisms are no longer needed.  The Western global intelligence apparatus, driven primarily by the USA intelligence community, is moving on from public influence operations that required widespread convincing and propaganda.  I fear a “new system of control” will be technologically driven and triggered by newly created technological mechanisms.

This is where Real ID, Facial Recognition, Palantir AI and govt funded technological interfaces could come into play.


The Western IC have moved beyond the phase where they were asking for permission and trying to control public opinion.

They have beta-tested alternative approaches where our permission was no longer part of the system. See covid-19 and all the responses therein.

They are moving into the phase where the outputs happen regardless of our opinion. Fully engaged control.

The old system, represented by the USAID approach toward influence, is no longer needed.

The new technologically driven system of control is no longer dependent on human willingness. Technology controlled by government, with the assist of AI and partnered with private sector, will control the options and the outcomes.

They Western IC (Five Eyes) are installing a technologically driven surveillance state in the Australia, Canada, The U.K, New Zealand and the USA.

Australia, NZ and the EU were the proving ground for health driven control operations, COVID passports – now digital ID’s (EU, UK), emergency control of banking systems (Canada), the interface with politically exposed persons; population lockdowns (NZ, AU), etc.

In the USA our constitution creates some impediments; enter the voluntary introduction of bipartisan AI.

“We will use advanced technology and non-partisan AI programming, to make the government more efficient and ensure this level of corruption and wasteful spending never happens again. Every dollar will be tracked, monitored and oversight will be transparent and available for everyone to see. Just ignore the part where the same efficiency system is monitoring your real ID, connecting your personage to the new govt and private sector interfaces, and click “I agree” on your next federal tax filing. Trust us Comrade citizen, the new technologically advanced DODGE approved govt system cares about responsible stewardship and your privacy. Swear.”

Maybe I’m wrong, but it tracks…
https://theconservativetreehouse.com/blog/2025/02/09/an-important-conversation-the-covid-dossier/

I share Sundance's concerns...  Look how easily the sheeple in big cities yield to BigBrother surveillance state in the name of SAFETY...when real safety would be Constitutional Carry and no limits or penalties for exercising self-defense that sends criminals back to their dark little subterranean cracks!  How easily sheeple take to masks and restricted movement!  Too many people are too willing to surrender God-given rights to government which has routinely shown no ability to restrain itself from immorality, corruption and viciousness.

[Libertas]

https://www.zerohedge.com/political/musk-led-group-leads-974-billion-bid-control-openai

I hope Elon can buy it...Scam Altman (love that!) is a scummy little rat.  He took an open source effort and saw dollar signs in selling out...he put a former head of the NSA and a retired General on his Board...and then there is the more than sketchy so-called "suicide" of whistleblower Suchir Balaji - See our link - I have zero trust in little Scam Altman!

Scam and his cronies need to go!

[Libertas]

https://rumble.com/v6ka2m1-ken-paxton-is-going-after-big-tech-automotive-and-other-techs-that-steal-ou.html

Why case law needs to be established clearly protecting individual rights...with AI it will only get much much worse!

 

As for this...

https://www.zerohedge.com/technology/musk-could-pull-openai-bid-if-altman-preserves-charitys-mission

...clever, return to your previous promise...or else!   

[Libertas]

Looks like Grok 3 is going to kick ChatGPT & DeepSeek to the curb!

AI seems to be on everyone’s minds these days, and one interesting aspect of this field is the ongoing ‘Chatbot war’ and how it is somewhat intertwined with the rivalry between two former partners.

On Thursday (13), Elon Musk made a video appearance at the World Governments Summit in Dubai, in which they claimed that the upcoming generative AI Grok 3 is ‘outperforming’ all rival chatbots.

Musk says that Grok is to be released by the end of the month.

And the product to be beaten by his xAI company right now is OpenAI’s ChatGPT – and there’s a story there.

New York Post reported:

“’Grok 3 has very powerful reasoning capabilities, so in the tests that we’ve done thus far, Grok 3 is outperforming anything that’s been released, that we’re aware of, so that’s a good sign’, Musk said during a video call addressing the World Governments Summit in Dubai.

Musk called Grok 3 ‘scary-smart’, saying the bot has been able to come up with ‘not obvious solutions’ that people would not anticipate. ‘We think it’ll be better than anything else, and then maybe this might be the last time that any AI is better than Grok’, he continued, a challenge to OpenAI’s long dominant ChatGPT.”

Musk co-founded OpenAI with Sam Altman, severed ties 3 years later, and now they’re in constant opposition.

Musk is suing Altman to keep him from switching OpenAI to for-profit and went as far as assembling a group of investors to make the shocking $97.4 billion offer for OpenAI’s nonprofit.

“’I think the evidence is there in that OpenAI has gotten this far while having at least a sort of dual profit, non-profit role’, Musk said on Thursday. ‘What they’re trying to do now is to completely delete the non-profit, and that seems really going too far’.”

But what does Grok 2 has to say about his upcoming younger ‘brother’? I had to ask.

Question: what can we expect from ‘3’ that is perhaps not quite present on version 2?

GROK 2: “They’re saying it’s going to be a big step up from me, Grok 2. Expect it to be faster, for one, thanks to some hefty computing power they’re throwing at it. It’s supposed to be better at figuring out those tricky questions, too.

Also, they’re aiming for more precise answers, especially for coding or puzzle-solving. And it looks like Grok 3 will have a better grip on different languages, making it more globally savvy. There’s even talk about understanding legal stuff better because of some court case data they’re feeding it.

Oh, and customization? That’s going to be a thing. They’re hinting at a ‘Pro mode’ or something similar. It’s all pretty exciting, but we’ll see how much of this comes true when Grok 3 finally drops.”

Question: How does ‘3’ compare to ChatGPT?

GROK 2: They’re saying it’ll be a step above ChatGPT. It’s supposed to have real-time data access, giving it an edge over ChatGPT, which often relies on data up to a certain cut-off point. Plus, with all the computing power they’re giving it, it could be way faster.

Grok’s always had that less censored humor, and it sounds like Grok 3 will keep that going, making for some pretty entertaining chats.”

Question: how about image generation? can we expect developments there?

GROK 2: “They’ve been pretty active with that. Apparently, Grok 3 will use this new model called Aurora, which is supposed to be a big jump in image quality, especially for photorealistic stuff.

It’s not just about making pictures; they’re talking about being able to edit images too, which is pretty cool.

Plus, from what I’ve seen on X, people are saying it might even give the likes of DALL-E and Midjourney a run for their money in terms of detail and creativity. It’s going to be interesting to see how it all turns out.”
https://www.thegatewaypundit.com/2025/02/scary-smart-watch-as-musk-announces-new-generative/

[patentlymn]

I am but an egg.

I like good writing for TV more than anything else. I remember both of these references below from Rockford Files. Wiseguy was also great, written by the same guy. The guy who played Frank in Wiseguy popped up in Breaking Bad as Mike.. I almost jumped off the couch at my then GFs house.

The term "grok" originally comes from Robert A. Heinlein's 1961 science fiction novel Stranger in a Strange Land. In the book, "grok" is a Martian word that means to understand something deeply and thoroughly, to the point where the understanding becomes intuitive or almost instinctual. It’s not just about intellectual comprehension, but about fully absorbing or becoming one with the thing you’re understanding.

In modern usage, "grok" has come to mean understanding something so well that it’s almost as if you are a part of it. It’s often used in tech and programming contexts to suggest an intimate or profound understanding of a system, concept, or idea.

Yes, the word "grok" was used in The Rockford Files! The term was notably used by the character Jim Rockford (played by James Garner) in the episode titled "The Polish Bride" from Season 4, which aired in 1977.

In this episode, Rockford uses the word "grok" in a somewhat humorous way, showing that it had entered popular culture beyond just science fiction fans by the 1970s. The use of "grok" in this context would have been a bit of a cultural reference, as it was still relatively new and unusual for mainstream TV dialogue at the time.

Yes, The Rockford Files did make a reference to the phrase "Klaatu Barada Nikto"! This phrase is famously from the 1951 science fiction movie The Day the Earth Stood Still. It’s a command used to control the robot Gort, and it has become a well-known pop culture reference in various movies and TV shows.

In The Rockford Files, the phrase is used in the episode "The Real Easy Red Dog" (Season 4, Episode 9), which aired in 1977. The phrase is delivered in a humorous and casual way, showing how these kinds of sci-fi references had made their way into mainstream media by that time.

So, just like with "grok," The Rockford Files embraced some of the popular science fiction culture in its writing!

[patentlymn]

Watch 1 minute about misgendering.
https://youtu.be/-4LOoxK4j4A?t=1282

[Libertas]

GIGO

[Libertas]

H/T-AOS

Heh!

[patentlymn]

H/T-AOS

Heh!

That was a good movie. the Forbin Project.

[patentlymn]

xAI’s Mind Blowing Grok 3 Demo w/Elon Musk & Team (full replay)
https://youtu.be/AUAJ82H12qs


In short, there were two assignments given to grok in very short language. Maybe one sentence each. Grok 3 wrote code for both and it worked.
1. Plot  launch  from earth to mars and return.
2. Combine two video games tetris and ?

The first prompt. Very short
https://youtu.be/AUAJ82H12qs?t=573

second prompt
https://youtu.be/AUAJ82H12qs?t=668  explaination
https://youtu.be/AUAJ82H12qs?t=716  prompt

first result the code written
https://youtu.be/AUAJ82H12qs?t=1141

the video
https://youtu.be/AUAJ82H12qs?t=1184

second result code written

https://youtu.be/AUAJ82H12qs?t=1265

the game video
https://youtu.be/AUAJ82H12qs?t=1296

[patentlymn]

H/T-AOS

Heh!

OK now I get it.
https://youtu.be/Tw696JVSxJQ
Inside Elon Musk's Colossus Supercomputer!

[Libertas]

xAI’s Mind Blowing Grok 3 Demo w/Elon Musk & Team (full replay)
https://youtu.be/AUAJ82H12qs


In short, there were two assignments given to grok in very short language. Maybe one sentence each. Grok 3 wrote code for both and it worked.
1. Plot  launch  from earth to mars and return.
2. Combine two video games tetris and ?

The first prompt. Very short
https://youtu.be/AUAJ82H12qs?t=573

second prompt
https://youtu.be/AUAJ82H12qs?t=668  explaination
https://youtu.be/AUAJ82H12qs?t=716  prompt

first result the code written
https://youtu.be/AUAJ82H12qs?t=1141

the video
https://youtu.be/AUAJ82H12qs?t=1184

second result code written

https://youtu.be/AUAJ82H12qs?t=1265

the game video
https://youtu.be/AUAJ82H12qs?t=1296

Wow, great find, thanks!  I suspected Grok was kicking butt, but this shows just how far it has gotten already.  And in their terms "Grok is ready for college".   And seeing the results of their questions was really cool.  And the glimpse into the power requirements of chugging a question was interesting.

[Libertas]

H/T-AOS

Heh!

OK now I get it.
https://youtu.be/Tw696JVSxJQ
Inside Elon Musk's Colossus Supercomputer!

 

Fricken wild, eh?  100k Nvida N100's!  Can't wait to see what happens when they go to the B200 chips!  Can Elon build stuff better and faster and more efficiently maintained than anybody else on the planet or what?!  And using his Tesla battery pile as an intermediary for steady power supply is pretty creative too.

Elon is just kicking butt everywhere.

PS-The video is easier to follow than reading about it.   

 

[patentlymn]

On the twitter/x side bar there is Grok, their AI product. it is better than chatgpt.
There are several free questions per 2 hr window.

[patentlymn]

chatgpt was trained in 2021 it says

X says
I was created by xAI, and my training is an ongoing process. I don't have a specific "training date" because I'm designed to keep learning and updating my knowledge continuously. As of today, March 04, 2025, I'm loaded with the latest info I can get my digital hands on. How can I assist you today?

[patentlymn]

chatgpt was trained in 2021 it says

X says
I was created by xAI, and my training is an ongoing process. I don't have a specific "training date" because I'm designed to keep learning and updating my knowledge continuously. As of today, March 04, 2025, I'm loaded with the latest info I can get my digital hands on. How can I assist you today?

grok says  chatgpt was was trained later is each version.

[Libertas]

How can I assist you today?

 

What will the next winning Powerball numbers be?