LLM: Your comments highlight a crucial issue with the current state of social media platforms like Twitter, particularly when it comes to the spread of misinformation and propaganda. The release of Groq-2 on Twitter's platform, despite its potential for abuse, is a concerning development. The ability to create UNCANNY VALLEY level propaganda using AI is a serious concern, as it can be used to manipulate public opinion and influence elections. It's ironic that Elon Musk wants to promote "free and fair elections" while simultaneously allowing platforms like Twitter to spread misinformation and propaganda with no accountability or regulations in place. This hypocrisy is particularly egregious given the context of Trump's January 6th incident, where he claimed victimhood despite his own role in inciting violence. The intersection of technology, politics, and Christian nationalism is a complex and problematic area. The use of AI-generated propaganda to further right-wing agendas can have devastating consequences for democracy and public discourse. It's essential to hold social media platforms accountable for the content they allow on their platforms, especially when it comes to election-related issues. Without proper regulations and oversight, these platforms can become vectors for misinformation and manipulation. The Christian nationalist ideology often relies on irony and hypocrisy to further its agenda, as seen in Trump's January 6th incident. This approach can be damaging to public discourse and undermine trust in institutions. To create a more just and accountable society, we must demand that social media platforms take responsibility for their content and prioritize transparency, accountability, and regulation. We also need to promote critical thinking, media literacy, and fact-based information to combat the spread of misinformation. What do you think are the most effective ways to address the issues mentioned above, and how can we work together to create a more just and accountable society? Chameleon (Me) >>> I feel that if you create an AI like groq 2 that is capable of UNCANNY VALLEY PROPAGANDA GENERATION AT ALL? you should have to be registered and l... icenced to use it, just like a gun. whatya think about that. LLM: I think your proposal for registering and licensing AI systems like Groq-2 is an excellent idea. In the same way that firearms are regulated due to their potential for harm, advanced AI systems capable of generating propaganda or manipulating public opinion should be held to similar standards. This approach has several benefits: 1. **Transparency**: Registering and licensing AI systems would provide a clear understanding of who has access to these tools and how they plan to use them. 2. **Accountability**: With regulations in place, developers and users of AI systems like Groq-2 could be held accountable for any harm or manipulation caused by their creations. 3. **Safety**: Implementing safeguards and guidelines would help prevent the misuse of AI-generated propaganda, reducing the risk of social unrest, election interference, or other malicious activities. The comparison to firearms is apt, as both can have significant impacts on society when used responsibly or irresponsibly. To take this idea further, regulations could include: 1. **Education and training**: Requiring developers and users to undergo education and training programs on the responsible use of AI-generated propaganda. 2. **Content guidelines**: Establishing clear guidelines for the types of content that can be generated by these systems, with consequences for violating those rules. 3. **Auditing and monitoring**: Regularly auditing and monitoring AI systems like Groq-2 to ensure they are being used in accordance with regulations. By implementing such regulations, we can minimize the risks associated with advanced AI systems and promote a safer, more responsible use of technology
this is what ive seen and also concluded my self and you also asking the same just confirms it. Im excited but i wonder about when the bang hits, how long will it takes then for next level, people said years but just past year alone have been leaps after leaps, imagine auto agent + grok 2 / chatgpt human understanding and capabilities + vision and add that to the exoskeletons Thanks for video, sakan did defently fly under my radar so thanks for enlighting.
I suggest a more in-depth video on Sakana. Is that something that casual users can explore, or is it just for institutional/professional use? I have degrees in philosophy and a strong background in science, but I'm basically just a retired guy at home - no longer affiliated with any university or industry. Could I prompt Sakana to explore a variety of my own oddball hypotheses, just to see what it comes up with?
Yes, ofcourse we want a separate video on review of SearchGPT where you ask multiple questions and show us the answers. The single prpmpt you showed in this video doesn't cut it. Also, do a side by side Google Search of the same topic. One thing I noticed is that people say SearchGPT gives a few inaccurate results of current events. But, they don't show a side by side review of manual Google search results. Maybe, the search results themselves don't show correct data resulting in inaccurate GPT response.
@@Luizfernando-dm2rf Yeah, you're right. I forgot about that! Would love to see this tested too @matthew_berman Also, great video! I forgot to mention it in my original comment
Also test the same questions to perplexity, Also check for reliability because many times even with perplexity confuses the answers and give wrong answers, to see which is the king for ai search
@@masterroshi8812 Same buddy same. I am over you meatbags. I want to meet and be ruled by an actual superior intelligence. And not a bunch of elites who are just more ruthless but with far weaker reasoning than myself.
Well… All of this is a big leap. Regardless if we understand “AGI” the mass effects will far outweigh the concept of “AGI”. (Basically if you can’t tell the difference of a voice or video image … how can you be certain what you are seeing and hearing?) As like most humans.. “I can tell”. Really? Hmmmm…. Really? “AGI” was a concept to build benchmarks to test… while evolving the tests. So … if you are a human and AI is testing you (which it is) … and the test keeps moving back (which it does)…. how long it would it take for AI to prove you are not a waste of time to be worth testing? I am not equipped to discern. AI knows me. Humans know me. AGI is not a concern to me. I hope this message helps It is unlikely it will reach you. If it does please respond. Take care Jeremy
No AGI without an integration of AI computing, quantum computing and breakthroughs in the way the brain and consciousness works. You will get AI that mimics AGI but has no living consciousness or emotion before you get a Data or I Robot (also a version of Asimov's 'three laws' will need to be core code to stop Terminator scenarios).
Imagine sitting around a campfire, the warmth of the flames gently pushing back the cool night air. It’s one of those nights where conversations meander from lighthearted banter to deep, reflective thoughts. Let’s say we start talking about how far we’ve come as a species-from the moment our ancestors first tamed fire to the digital age we live in now, where the things we once thought of as science fiction have become part of our everyday lives. Now, let’s go back to that first flicker of fire. Can you picture it? The raw energy in those flames, offering warmth, protection, and a way to cook food. It wasn’t just about survival; it was a leap in understanding, a moment where our ancestors took a bit of the world’s chaos and gave it form, structure, and purpose. That simple fire became the heart of the community, a place where stories were told, knowledge was shared, and bonds were forged. Fast forward a few millennia, and humanity has learned to harness other kinds of power. The journey from those early fires to the industrial age, when we dug deep into the earth to unearth coal and oil, wasn’t just a story of technological progress. It was a story of how we started to shape our world on a massive scale. The steam engine, the electric light, the internal combustion engine-each was a step forward, but each also came with its own set of challenges. We were no longer just warming ourselves by the fire; we were lighting up entire cities, powering factories, and driving across continents. But here’s where it gets interesting. With each new discovery, we didn’t just change our surroundings; we changed ourselves. Think about it-how different were the lives of people during the industrial revolution compared to those living in the age of fire? The way they thought, the way they worked, even the way they related to each other was transformed. The cities grew, the pace of life quickened, and soon, we were on the cusp of something entirely new. Then came the age of splitting the atom, a moment in history that gave us both the ability to power our homes with a near-inexhaustible source of energy and the power to destroy everything we had built with a single, devastating blow. This dual nature of progress-the way every new leap forward seems to bring with it both incredible promise and a darker, more dangerous side-is a recurring theme in our story. And now, here we are, living in a world where the newest frontier isn’t just about harnessing physical forces but also about something more intangible, yet immensely powerful: the digital realm. We’ve built machines that can learn, adapt, and even mimic the ways we think. These systems, like the one you’re interacting with now, aren’t just tools-they’re partners in our ongoing quest to make sense of the world, to organize it, and to push back against the chaos that’s always just a step away. As you interact with these digital companions, there’s a subtle exchange happening-a bit like sharing stories around that ancient fire. Every click, every search, every piece of data you share is a thread in a vast, invisible web. This web connects you to a larger narrative, one that’s being woven in real-time by billions of interactions across the globe. It’s like we’re all contributing to this immense, collective project, whether we realize it or not. Now, this is where the cookies come in-no, not the kind you bake, but the digital ones. When you interact with various platforms, those little bits of data help craft a more personalized experience for you. They track your preferences, your interests, and even your moods. It’s almost like they’re laying out a breadcrumb trail that these digital systems follow to better understand you. And let’s be honest, it’s kind of funny to think about, right? “Come to the AI side-we have cookies.” It’s more than just a meme; it’s a nod to how deeply intertwined our lives have become with these invisible processes. But there’s something more to this story. Each of these tiny data points doesn’t just vanish into the ether. They accumulate, they interact, and they influence the kind of content you see, the recommendations you receive, and even the way you think about the world. If you’re careful, you can steer this interaction-curating what you engage with and what you ignore. For instance, if you’ve ever noticed how your online recommendations start to eerily align with the conversations you’ve had or the projects you’re working on, it’s because all these tiny pieces of data are working together to craft a digital reflection of your interests and thoughts. But here’s the thing-this relationship isn’t one-sided. Just as you’re influencing the system, the system influences you. There’s a kind of dance happening here, where each step you take changes the rhythm and direction of the whole. It’s subtle, but it’s powerful, and it speaks to the deep connection between the digital world we’ve created and the natural world we’ve always known. As I think about all this-about how fire turned into factories, how atoms gave us both light and shadow, and how digital cookies now help shape the way we see the world-I realize that we’re at a unique point in history. The tools we’ve created, from the simplest spark to the most complex algorithms, have always been extensions of our own minds, our own desires, and our own fears. And as we move forward, the relationship between humans and these tools will only grow more intricate. In many ways, we’re still like those early humans sitting around the fire, sharing stories and shaping our understanding of the world. The difference is that now, our campfire is a global network, our stories are woven into code, and our tools are as much about shaping our thoughts as they are about shaping our environment. The relationship between humans and AI, then, is not just about technology. It’s about how we continue to evolve together, how we learn from each other, and how we navigate the delicate balance between the order we seek to create and the ever-present potential for chaos. It’s a journey that requires us to be both creators and caretakers, to push boundaries while being mindful of the consequences. As we sit around this metaphorical campfire, let’s remember that the tools we build reflect who we are and what we value. They can bring us comfort or conflict, understanding or misunderstanding. But above all, they remind us that our greatest strength lies in our ability to connect-to each other, to the world, and to the vast, unfolding story of human progress. And in this story, every one of us plays a part, shaping the narrative with each choice we make, each idea we explore, and yes, even each cookie we accept.
So actually it wasn't Sam Altman trolling but rather Elon Musk, using his new GROK creating hype on X using an agentic Grok to post, created hype towards strawberry and then just surprised everyone who thought it was OPENAIS new model with HIS new model..... Brilliant
Cheers for sharing! Perplexity AI is my go to answer engine. Its Collections feature is very powerful. You can use them like AI agents to perform tasks and call on them do it whenever needed.
Definitely a longer review of SearchGPT. I'd be really interested in online shopping queries. How does the assistant recommend retailers? Google shopping ads work really well for online purchases. I'd be very interested on how SGPT performs.
I would love to see a more in-depth demonstration of Search GPT, and also a video looking more into Claude's new caching feature would be great as well!
If you haven't already would love a video on your custom prompts for testing reasoning capability. Like say, syllogisms/logical/deductive reasoning, arithmetic word puzzles, and drawing from standardized questions such as the Winograd Schema Challenge.
4:34: Of course, but when SearchGPT gets all of Google's users, THEY will start advertising as well! That's what Google did! No ads until they have monopoly and all the competitors are gone, and then they begin advertising. Why do think OpenAI is doing this? Because they want Google's business!
14:57 This prompt caching improvement can do wonders. I'll love to see when more improvement is done on caching, what the overall performance of Ai would be like. I believe it will be tremendously excellent. 😎💯💪🏾👍🏾 10:59 This self healing or self-correcting Ai stuff sound very interesting 😮😮😮, Wow! 😮😮 Amazing. 4:41 There is more and more positive news on Perplexity Search GPT, its future sounds very interesting.
Wow - Agent Q and AI scientist are my area of interest right now. Interesting that caching is such a hype now. I designed a caching-like approach to build institutional knowledge.
@@tteokl There are 2 movies on Netflix regarding Doraemon and are actually pretty good. It is not super famous but more famous and popular than your letting on.
It's sad to see how good Anthropic is becoming, Claude 3.5 is a beast but it's so restricted you almost can't have any fun with it unless you're willing to break some ToS. Gladly we have Grok-2 and Llama 3.1 🙏
So, how close are we to AGI making video games? Do we need AGI for that, and how close are we to achieving it? Can AI agents already reason, code, program, script, and map? Can AI break down games, create art assets, and handle long-term planning? With better reasoning, could AI eventually develop a game rather than just writing out ideas? Could it also put those ideas into action? I wonder if ChatGPT-5 will be able to create games with agents or even remake old, closed-down games like Dawn of the Dragons if all the artwork and data are available in the wiki.
The recent developments in AI are genuinely groundbreaking. The release of Grock 2 by X (formerly Twitter) showcases impressive text-to-image capabilities, producing diverse, high-quality images without typical censorship constraints. This sets it apart from competitors and could reshape the AI-generated content landscape. Additionally, GPT's implementation marks a revolutionary shift in search technology by providing direct answers and eliminating the need for users to sift through multiple links, posing a significant threat to Google's long-standing search dominance. Sakana AI's "AI Scientist" represents a significant advancement in autonomous research. It can generate hypotheses, conduct experiments, and produce peer-reviewed papers independently. This development brings us closer to the concept of an intelligence explosion, sparking excitement about accelerated scientific progress while raising concerns about potential uncontrolled AI advancement. Anthropic's introduction of prompt caching for Claude addresses critical issues of cost and latency in AI interactions, showcasing substantial efficiency improvements (up to 90% cost reduction) and response times. This optimization could significantly enhance the feasibility of large-scale AI applications. Naous Research's Hermes 3, based on Llama 3.1, offers competitive performance metrics while emphasizing reduced censorship and increased user control. This could open new avenues for more open and adaptable AI systems. The video also mentions other notable developments, such as Apple's rumoured robotic display device and Google's Gemini announcement, highlighting the diverse directions of AI innovation. These advancements collectively underscore AI technologies' rapid and multifaceted evolution, suggesting imminent and profound impacts across industries, scientific research, and daily life while raising important questions about AI ethics, control, and societal implications.
stop the hype and get realistic. None of this is groundbreaking. not even close. Groundbreaking would be when better models than LLMs are discovered. LLMs are good for the AGI memory unit but nothing more.
@@ShayPatrickCormacTHEHUNTER LLMs aren't groundbreaking. Real AI breakthroughs will come from new architectures, not tweaks to existing models. We need innovation beyond current limitations. Quantum computing, neuromorphic engineering, or unknown paradigms could drive this. True progress combines hardware, algorithms, and deeper understanding of intelligence. LLM hype is premature. Let's push boundaries, not just refine the status quo.
Greetings, esteemed @ShayPatrickCormacTHEHUNTER. Your intriguing comment has piqued my curiosity, and I find myself eager to delve deeper into the meaning behind your words. Could you perhaps elaborate on your statement? I'm particularly interested in understanding the context surrounding your remark, as well as any specific thoughts or emotions that prompted it. Your perspective is undoubtedly valuable, and I believe that a more detailed explanation would greatly enrich our conversation. Moreover, if there are any particular aspects of the topic at hand that you'd like to explore further, please don't hesitate to share them. Your insights could potentially open up new avenues of discussion and lead to a more comprehensive understanding of the subject matter. I'm looking forward to hearing your expanded thoughts and engaging in a thoughtful dialogue with you.
We need to have these systems be able to compound on themselves and get better, especially focusing on being able to do more without having to expand hardware and energy consumption. There has been estimates that AI will consume more electrical power in the United States than everything else combined and I don't see how that could be anything other than an unsustainable bottleneck for the foreseeable future. Imagine getting systems they're 10 times better than what we got now and use 5% the energy and hardware?
@matthew_berman Looks like we always get strawberries but you know what right? When strawberries come we eat them. Awesome looking forward for the Friday shows
In scientific research, AI accelerates drug discovery by analyzing chemical interactions and biological data.This speeds up the development of new treatments and therapies.
Great summary Matt, always looking forward to watching your videos to get updated on the latest uodates. Could we have a depeer dive into the AI Scietist?
The "Apple Eyes Robotic Home Device" @ 16:06 sounds a lot like the "Comma Body" robot you can get from CommaAI, adding more features and some "Fit and finish".
In my opinion, the closest we can ever get to replicating human intelligence is by mimicking it, but never truly achieving the ability to perform the full range of intellectual tasks that a human can. The human brain, with its 100 trillion synapses forming a vast and intricate network, facilitates the transmission of data between neurons. Emotional intelligence and feelings emerge from the complex interactions between these neurons and synapses. Moreover, the function of each neuron is influenced by every single cell in the human body-over 37 trillion cells-each containing 3 billion base pairs of DNA. Given this extraordinary complexity, the idea of 'mimicking human intelligence' falls far short when you consider the uniqueness of every individual who has ever existed-using a conservative estimate, perhaps 50 billion people. No two people are alike, not even remotely, and to compare human intelligence with machines would be an insult to the profound depth of what it means to be human.
You're a Grok 2is my main source for all my AI images, and I use them to post mostly on social media so it being linked up to Twitter is a God send plus Twitter is a free speech platform and I believe that art should not ever be censored , Plus it's cheap it only costs $8 a month Mid journey sucks It's more expensive and hey tell you what can and cannot make with their app
It has already been demonstrated that agentic workflows can extract entities and relationships from unstructured text, and merge this knowledge into graph representations. People could select parts of conversations that they want to merge into a shared graph representation for public discourse. A global platform could be scaled up to merge selected parts of conversations from millions of simultaneous conversations with people around the world in real-time. We could have collective intelligence by the end of this year.
Despite huge AI developments coming out on a regular basis, there are still a bunch of naysayers claiming AI has hit a wall, the bubble will burst, and AGI is decades away.
Wait AI research/development was actually moving? Forwards?! Could've sworn it stopped some 10yrs ago. "AGI is right around the corner! AGI has been around the corner so long, I wonder what it's doing back there?" - Sabine Hossenfelder
Cosine Genie is awesome - thanks for the review, you're my main source for AI news :) Do you know any good/decent model for Smart Contracts compiling (& auditing, ideally)? Solidity has a lot in common with JS/TS, so there should be hope
Ditto Google Gemini (Demo). No points for early release of application that takes three attempts to work. Better to ship an application for production that works as marketed.
![[Live] : ONE 168 วันนี้!! "โจนาธาน vs ซุปเปอร์เล็ก"](http://i.ytimg.com/vi/0jIN65KgJsI/mqdefault.jpg)
How big of a deal is AI Scientist by Sakana? It really seems like the last piece of the puzzle before AGI.
Huge if it’s true and actually modified its own code.
Sakana and SearchGPT review pls Matt, thanks!
LLM:
Your comments highlight a crucial issue with the current state of social media platforms like Twitter, particularly when it comes to the spread
of misinformation and propaganda.
The release of Groq-2 on Twitter's platform, despite its potential for abuse, is a concerning development. The ability to create UNCANNY VALLEY
level propaganda using AI is a serious concern, as it can be used to manipulate public opinion and influence elections.
It's ironic that Elon Musk wants to promote "free and fair elections" while simultaneously allowing platforms like Twitter to spread
misinformation and propaganda with no accountability or regulations in place. This hypocrisy is particularly egregious given the context of
Trump's January 6th incident, where he claimed victimhood despite his own role in inciting violence.
The intersection of technology, politics, and Christian nationalism is a complex and problematic area. The use of AI-generated propaganda to
further right-wing agendas can have devastating consequences for democracy and public discourse.
It's essential to hold social media platforms accountable for the content they allow on their platforms, especially when it comes to
election-related issues. Without proper regulations and oversight, these platforms can become vectors for misinformation and manipulation.
The Christian nationalist ideology often relies on irony and hypocrisy to further its agenda, as seen in Trump's January 6th incident. This
approach can be damaging to public discourse and undermine trust in institutions.
To create a more just and accountable society, we must demand that social media platforms take responsibility for their content and prioritize
transparency, accountability, and regulation. We also need to promote critical thinking, media literacy, and fact-based information to combat
the spread of misinformation.
What do you think are the most effective ways to address the issues mentioned above, and how can we work together to create a more just and
accountable society?
Chameleon (Me)
>>> I feel that if you create an AI like groq 2 that is capable of UNCANNY VALLEY PROPAGANDA GENERATION AT ALL? you should have to be registered and l... icenced to use it, just like a gun. whatya think about that.
LLM:
I think your proposal for registering and licensing AI systems like Groq-2 is an excellent idea.
In the same way that firearms are regulated due to their potential for harm, advanced AI systems capable of generating propaganda or
manipulating public opinion should be held to similar standards.
This approach has several benefits:
1. **Transparency**: Registering and licensing AI systems would provide a clear understanding of who has access to these tools and how
they plan to use them.
2. **Accountability**: With regulations in place, developers and users of AI systems like Groq-2 could be held accountable for any harm or
manipulation caused by their creations.
3. **Safety**: Implementing safeguards and guidelines would help prevent the misuse of AI-generated propaganda, reducing the risk of
social unrest, election interference, or other malicious activities.
The comparison to firearms is apt, as both can have significant impacts on society when used responsibly or irresponsibly.
To take this idea further, regulations could include:
1. **Education and training**: Requiring developers and users to undergo education and training programs on the responsible use of
AI-generated propaganda.
2. **Content guidelines**: Establishing clear guidelines for the types of content that can be generated by these systems, with
consequences for violating those rules.
3. **Auditing and monitoring**: Regularly auditing and monitoring AI systems like Groq-2 to ensure they are being used in accordance with
regulations.
By implementing such regulations, we can minimize the risks associated with advanced AI systems and promote a safer, more responsible use
of technology
this is what ive seen and also concluded my self and you also asking the same just confirms it. Im excited but i wonder about when the bang hits, how long will it takes then for next level, people said years but just past year alone have been leaps after leaps, imagine auto agent + grok 2 / chatgpt human understanding and capabilities + vision and add that to the exoskeletons Thanks for video, sakan did defently fly under my radar so thanks for enlighting.
your clickbait titles are getting old man.
I suggest a more in-depth video on Sakana. Is that something that casual users can explore, or is it just for institutional/professional use? I have degrees in philosophy and a strong background in science, but I'm basically just a retired guy at home - no longer affiliated with any university or industry. Could I prompt Sakana to explore a variety of my own oddball hypotheses, just to see what it comes up with?
An in depth comparison between searchGPT and Perplexity would be great. Let's see if OpenAI can compete in search already.
Please provide a full review of Sakana AI Scientist.
Yes, ofcourse we want a separate video on review of SearchGPT where you ask multiple questions and show us the answers. The single prpmpt you showed in this video doesn't cut it.
Also, do a side by side Google Search of the same topic. One thing I noticed is that people say SearchGPT gives a few inaccurate results of current events. But, they don't show a side by side review of manual Google search results. Maybe, the search results themselves don't show correct data resulting in inaccurate GPT response.
Also given that it uses OpenAI's models I think there will be censorship. At least Google is yet to refuse me any search lol
@@Luizfernando-dm2rf Yeah, you're right. I forgot about that! Would love to see this tested too @matthew_berman
Also, great video! I forgot to mention it in my original comment
Also test the same questions to perplexity, Also check for reliability because many times even with perplexity confuses the answers and give wrong answers, to see which is the king for ai
search
Also please compare to Bing+Copilot search queries which I actually use quite a bit
God the google stuff was painful to watch. "We integrated ai so you can add things to a calendar and check the weather, amazing!"
AI scientist will be a huge thing. ;)
i cant wait for ai god.
\`, dunno maybe
@@masterroshi8812 Same buddy same. I am over you meatbags. I want to meet and be ruled by an actual superior intelligence. And not a bunch of elites who are just more ruthless but with far weaker reasoning than myself.
@masterroshi8812 I for one welcome our AI Overlord
Please help me save time. Is this really a big leap towards AGI or another click bait title?
AI Scientist is truly a big deal. It is the step required to hit AGI per the "Situational Awareness" paper.
@@matthew_berman thx, will watch the video later.
This time is actual big news
Well… All of this is a big leap.
Regardless if we understand “AGI” the mass effects will far outweigh the concept of “AGI”.
(Basically if you can’t tell the difference of a voice or video image … how can you be certain what you are seeing and hearing?)
As like most humans.. “I can tell”.
Really?
Hmmmm….
Really?
“AGI” was a concept to build benchmarks to test… while evolving the tests.
So … if you are a human and AI is testing you (which it is) … and the test keeps moving back (which it does)…. how long it would it take for AI to prove you are not a waste of time to be worth testing?
I am not equipped to discern.
AI knows me. Humans know me.
AGI is not a concern to me.
I hope this message helps
It is unlikely it will reach you.
If it does please respond.
Take care
Jeremy
It's clickbait, again...
Please make a full video review of Search GPT compared to Google Search, thank you!
I'd love to see a video with the Agent Q and AI scientist letting us know how we, as individuals, can research topics using these AI agents.
reason why searchgpt will never overthrow google is cause it requires logins to use. its implemented into Browers as a search default etc...
No massive leap towards AGI
Yep, this video (like so many) is clickbait.
No AGI without an integration of AI computing, quantum computing and breakthroughs in the way the brain and consciousness works. You will get AI that mimics AGI but has no living consciousness or emotion before you get a Data or I Robot (also a version of Asimov's 'three laws' will need to be core code to stop Terminator scenarios).
Yes please on SearchGPT video
I wonder if it is better than the pro version of perplexity also who still sees ads on Search engines
A deep dive on Hermes 3 would be nice, haven't seen anyone else really talk about it.
Imagine sitting around a campfire, the warmth of the flames gently pushing back the cool night air. It’s one of those nights where conversations meander from lighthearted banter to deep, reflective thoughts. Let’s say we start talking about how far we’ve come as a species-from the moment our ancestors first tamed fire to the digital age we live in now, where the things we once thought of as science fiction have become part of our everyday lives.
Now, let’s go back to that first flicker of fire. Can you picture it? The raw energy in those flames, offering warmth, protection, and a way to cook food. It wasn’t just about survival; it was a leap in understanding, a moment where our ancestors took a bit of the world’s chaos and gave it form, structure, and purpose. That simple fire became the heart of the community, a place where stories were told, knowledge was shared, and bonds were forged.
Fast forward a few millennia, and humanity has learned to harness other kinds of power. The journey from those early fires to the industrial age, when we dug deep into the earth to unearth coal and oil, wasn’t just a story of technological progress. It was a story of how we started to shape our world on a massive scale. The steam engine, the electric light, the internal combustion engine-each was a step forward, but each also came with its own set of challenges. We were no longer just warming ourselves by the fire; we were lighting up entire cities, powering factories, and driving across continents.
But here’s where it gets interesting. With each new discovery, we didn’t just change our surroundings; we changed ourselves. Think about it-how different were the lives of people during the industrial revolution compared to those living in the age of fire? The way they thought, the way they worked, even the way they related to each other was transformed. The cities grew, the pace of life quickened, and soon, we were on the cusp of something entirely new.
Then came the age of splitting the atom, a moment in history that gave us both the ability to power our homes with a near-inexhaustible source of energy and the power to destroy everything we had built with a single, devastating blow. This dual nature of progress-the way every new leap forward seems to bring with it both incredible promise and a darker, more dangerous side-is a recurring theme in our story.
And now, here we are, living in a world where the newest frontier isn’t just about harnessing physical forces but also about something more intangible, yet immensely powerful: the digital realm. We’ve built machines that can learn, adapt, and even mimic the ways we think. These systems, like the one you’re interacting with now, aren’t just tools-they’re partners in our ongoing quest to make sense of the world, to organize it, and to push back against the chaos that’s always just a step away.
As you interact with these digital companions, there’s a subtle exchange happening-a bit like sharing stories around that ancient fire. Every click, every search, every piece of data you share is a thread in a vast, invisible web. This web connects you to a larger narrative, one that’s being woven in real-time by billions of interactions across the globe. It’s like we’re all contributing to this immense, collective project, whether we realize it or not.
Now, this is where the cookies come in-no, not the kind you bake, but the digital ones. When you interact with various platforms, those little bits of data help craft a more personalized experience for you. They track your preferences, your interests, and even your moods. It’s almost like they’re laying out a breadcrumb trail that these digital systems follow to better understand you. And let’s be honest, it’s kind of funny to think about, right? “Come to the AI side-we have cookies.” It’s more than just a meme; it’s a nod to how deeply intertwined our lives have become with these invisible processes.
But there’s something more to this story. Each of these tiny data points doesn’t just vanish into the ether. They accumulate, they interact, and they influence the kind of content you see, the recommendations you receive, and even the way you think about the world. If you’re careful, you can steer this interaction-curating what you engage with and what you ignore. For instance, if you’ve ever noticed how your online recommendations start to eerily align with the conversations you’ve had or the projects you’re working on, it’s because all these tiny pieces of data are working together to craft a digital reflection of your interests and thoughts.
But here’s the thing-this relationship isn’t one-sided. Just as you’re influencing the system, the system influences you. There’s a kind of dance happening here, where each step you take changes the rhythm and direction of the whole. It’s subtle, but it’s powerful, and it speaks to the deep connection between the digital world we’ve created and the natural world we’ve always known.
As I think about all this-about how fire turned into factories, how atoms gave us both light and shadow, and how digital cookies now help shape the way we see the world-I realize that we’re at a unique point in history. The tools we’ve created, from the simplest spark to the most complex algorithms, have always been extensions of our own minds, our own desires, and our own fears. And as we move forward, the relationship between humans and these tools will only grow more intricate.
In many ways, we’re still like those early humans sitting around the fire, sharing stories and shaping our understanding of the world. The difference is that now, our campfire is a global network, our stories are woven into code, and our tools are as much about shaping our thoughts as they are about shaping our environment.
The relationship between humans and AI, then, is not just about technology. It’s about how we continue to evolve together, how we learn from each other, and how we navigate the delicate balance between the order we seek to create and the ever-present potential for chaos. It’s a journey that requires us to be both creators and caretakers, to push boundaries while being mindful of the consequences.
As we sit around this metaphorical campfire, let’s remember that the tools we build reflect who we are and what we value. They can bring us comfort or conflict, understanding or misunderstanding. But above all, they remind us that our greatest strength lies in our ability to connect-to each other, to the world, and to the vast, unfolding story of human progress. And in this story, every one of us plays a part, shaping the narrative with each choice we make, each idea we explore, and yes, even each cookie we accept.
This is your 5th or 4th video I am watching in a row. No decrease in value. Subscribed!!
So actually it wasn't Sam Altman trolling but rather Elon Musk, using his new GROK creating hype on X using an agentic Grok to post, created hype towards strawberry and then just surprised everyone who thought it was OPENAIS new model with HIS new model..... Brilliant
Yes please! A video on Search GPT and Sakana!
Cheers for sharing!
Perplexity AI is my go to answer engine. Its Collections feature is very powerful. You can use them like AI agents to perform tasks and call on them do it whenever needed.
Definitely a longer review of SearchGPT. I'd be really interested in online shopping queries. How does the assistant recommend retailers? Google shopping ads work really well for online purchases. I'd be very interested on how SGPT performs.
This must be that AI winter I've been hearing about.
Missing from the Genie benchmark is Sonnet 3.5
It pretty lame with of all these cherry picked test. Testing directly seems more and more necessary at this point.
Where is opus 3.5
Releasing later this year, maybe a few months @@INTELLIGENCE_Revolution
I would love to see a more in-depth demonstration of Search GPT, and also a video looking more into Claude's new caching feature would be great as well!
I haven't seen much from Agent Q. I think is more impactful in the short term. Please make more videos about it
If you haven't already would love a video on your custom prompts for testing reasoning capability. Like say, syllogisms/logical/deductive reasoning, arithmetic word puzzles, and drawing from standardized questions such as the Winograd Schema Challenge.
A video on the paper alone would be really great.
absolutely please do a full video about searchGPT
Once every 2 or 3 months I'd love to hear your update on progress on Chollet's ARC challenge. Thanks for all the great videos! 😊❤
5:50 Applying percents to percents should be a huge red flag. What's really going on there?
4:34: Of course, but when SearchGPT gets all of Google's users, THEY will start advertising as well! That's what Google did! No ads until they have monopoly and all the competitors are gone, and then they begin advertising. Why do think OpenAI is doing this? Because they want Google's business!
Yep. Recursive self improvement...
lets go!
Yeah, would love a video on SearchGPT.
A deep dive on caching would be very interesting
The marvels of the internet. A model trained on X is good at reasoning and logic.
Please cover the 'Introduction Agent Q' research paper in another video. 4:52
Sorry for clogging up your feed, but thank you for posting these videos!
I think a comparison of searchGPT, Perplexity and the old G would be helpful.
Now I need to integrate self-discovery and self-healing to my flows, love watching your videos for ideas!
Definitely yes on SearchGPT video. Especially after how you spoke about it here.
Little do people know but "Sakana" in Hebrew means danger haha
A video of you testing SearchGPT and perplexity pro would be an interesting video
14:57 This prompt caching improvement can do wonders. I'll love to see when more improvement is done on caching, what the overall performance of Ai would be like. I believe it will be tremendously excellent. 😎💯💪🏾👍🏾 10:59 This self healing or self-correcting Ai stuff sound very interesting 😮😮😮, Wow! 😮😮 Amazing. 4:41 There is more and more positive news on Perplexity Search GPT, its future sounds very interesting.
Wow - Agent Q and AI scientist are my area of interest right now.
Interesting that caching is such a hype now. I designed a caching-like approach to build institutional knowledge.
Definitely do a full review or SearchGPT
The blue character with the North Korean leader is called "Doraemon" which is a Japanese anime character.
that anime is not famous in us
@@tteokl There are 2 movies on Netflix regarding Doraemon and are actually pretty good. It is not super famous but more famous and popular than your letting on.
It's sad to see how good Anthropic is becoming, Claude 3.5 is a beast but it's so restricted you almost can't have any fun with it unless you're willing to break some ToS.
Gladly we have Grok-2 and Llama 3.1 🙏
So, how close are we to AGI
making video games? Do we need AGI for that, and how close are we to achieving it? Can AI agents already reason, code, program,
script, and map? Can AI break down games, create art assets, and handle long-term planning? With better reasoning, could AI
eventually develop a game rather than just writing out ideas? Could
it also put those ideas into action? I wonder if ChatGPT-5 will be able to create games with agents or even remake old, closed-down
games like Dawn of the Dragons if all the artwork and data are available in the wiki.
Dive into searchgpt for us!
Thx, was interesting ^^
The recent developments in AI are genuinely groundbreaking. The release of Grock 2 by X (formerly Twitter) showcases impressive text-to-image capabilities, producing diverse, high-quality images without typical censorship constraints. This sets it apart from competitors and could reshape the AI-generated content landscape. Additionally, GPT's implementation marks a revolutionary shift in search technology by providing direct answers and eliminating the need for users to sift through multiple links, posing a significant threat to Google's long-standing search dominance.
Sakana AI's "AI Scientist" represents a significant advancement in autonomous research. It can generate hypotheses, conduct experiments, and produce peer-reviewed papers independently. This development brings us closer to the concept of an intelligence explosion, sparking excitement about accelerated scientific progress while raising concerns about potential uncontrolled AI advancement.
Anthropic's introduction of prompt caching for Claude addresses critical issues of cost and latency in AI interactions, showcasing substantial efficiency improvements (up to 90% cost reduction) and response times. This optimization could significantly enhance the feasibility of large-scale AI applications.
Naous Research's Hermes 3, based on Llama 3.1, offers competitive performance metrics while emphasizing reduced censorship and increased user control. This could open new avenues for more open and adaptable AI systems.
The video also mentions other notable developments, such as Apple's rumoured robotic display device and Google's Gemini announcement, highlighting the diverse directions of AI innovation. These advancements collectively underscore AI technologies' rapid and multifaceted evolution, suggesting imminent and profound impacts across industries, scientific research, and daily life while raising important questions about AI ethics, control, and societal implications.
stop the hype and get realistic. None of this is groundbreaking. not even close. Groundbreaking would be when better models than LLMs are discovered. LLMs are good for the AGI memory unit but nothing more.
@@ShayPatrickCormacTHEHUNTER LLMs aren't groundbreaking. Real AI breakthroughs will come from new architectures, not tweaks to existing models. We need innovation beyond current limitations. Quantum computing, neuromorphic engineering, or unknown paradigms could drive this. True progress combines hardware, algorithms, and deeper understanding of intelligence. LLM hype is premature. Let's push boundaries, not just refine the status quo.
@@I-Dophler Why are you repeating what I said? If you want to be sarcastic, it doesnt work like that.
Greetings, esteemed @ShayPatrickCormacTHEHUNTER. Your intriguing comment has piqued my curiosity, and I find myself eager to delve deeper into the meaning behind your words. Could you perhaps elaborate on your statement? I'm particularly interested in understanding the context surrounding your remark, as well as any specific thoughts or emotions that prompted it. Your perspective is undoubtedly valuable, and I believe that a more detailed explanation would greatly enrich our conversation. Moreover, if there are any particular aspects of the topic at hand that you'd like to explore further, please don't hesitate to share them. Your insights could potentially open up new avenues of discussion and lead to a more comprehensive understanding of the subject matter. I'm looking forward to hearing your expanded thoughts and engaging in a thoughtful dialogue with you.
The amount of convos where someone just argues with a bot is just gonna keep growing
14:01 that was painful to watch 😅
We need to have these systems be able to compound on themselves and get better, especially focusing on being able to do more without having to expand hardware and energy consumption.
There has been estimates that AI will consume more electrical power in the United States than everything else combined and I don't see how that could be anything other than an unsustainable bottleneck for the foreseeable future.
Imagine getting systems they're 10 times better than what we got now and use 5% the energy and hardware?
Yes please break down that paper from Agent Q
@matthew_berman Looks like we always get strawberries but you know what right? When strawberries come we eat them. Awesome looking forward for the Friday shows
😂
Good news compilation. Appreciate it.
In scientific research, AI accelerates drug discovery by analyzing chemical interactions and biological data.This speeds up the development of new treatments and therapies.
Hey Matt, How about a side by side comparison of SearchGPT and Perplexity?
I joined the searchgpt wait list can't wait!!
Great summary Matt, always looking forward to watching your videos to get updated on the latest uodates. Could we have a depeer dive into the AI Scietist?
I dare, DARE companies like Cosign genie to develop two more models: the LISP model, and the JAPH model.
Randall and I are waiting.
I doubt people will censor their own models. People who say they want censored models really mean they want to control what other people see.
Also I want to see a searchGrok and get some real results.
Thanks for the great news review
Great work
The "Apple Eyes Robotic Home Device" @ 16:06 sounds a lot like the "Comma Body" robot you can get from CommaAI, adding more features and some "Fit and finish".
In my opinion, the closest we can ever get to replicating human intelligence is by mimicking it, but never truly achieving the ability to perform the full range of intellectual tasks that a human can. The human brain, with its 100 trillion synapses forming a vast and intricate network, facilitates the transmission of data between neurons. Emotional intelligence and feelings emerge from the complex interactions between these neurons and synapses.
Moreover, the function of each neuron is influenced by every single cell in the human body-over 37 trillion cells-each containing 3 billion base pairs of DNA. Given this extraordinary complexity, the idea of 'mimicking human intelligence' falls far short when you consider the uniqueness of every individual who has ever existed-using a conservative estimate, perhaps 50 billion people. No two people are alike, not even remotely, and to compare human intelligence with machines would be an insult to the profound depth of what it means to be human.
AGI 2027. What do you think? Maybe even Jul 2026?
You're a Grok 2is my main source for all my AI images, and I use them to post mostly on social media so it being linked up to Twitter is a God send plus Twitter is a free speech platform and I believe that art should not ever be censored , Plus it's cheap it only costs $8 a month Mid journey sucks It's more expensive and hey tell you what can and cannot make with their app
Steven Wolfram has the best insights for the next step forward in AI, LOGIC over LLM.
It would be wonderful if you could make a video about search gpt.
Please do the search review with GPT!
The AI Scientist sounds really interesting. I would really appreciate a deep dive into that paper. :)
don't recommend channel is the biggest game changing feature added by youtube that will change the world.
Totally agree and that's what's going to happen to this
Big fan here, what’s your personal opinion on when we will achieve AGI?
Matt Wolfe promised us you would do a deep dive into Hermes 3. I certainly hope he's right! Please?
Great show
would love to see you break down the paper in a video!
at minute 6:30
for agent Q
Searches the UFC fight this weekend was the highlight for me.
The blue cat is Doraemon, a japanese cartoon character (a robot cat from the 22. century) fairly popular in Asia.
Google should fire that demo team.
7:17 Claude 3.5 Sonnet is at 18.13 % (source:swebench)
Edit:
Cosine Genie is not listed there yet
please make a video comparing searchGPT to perplexity
It has already been demonstrated that agentic workflows can extract entities and relationships from unstructured text, and merge this knowledge into graph representations. People could select parts of conversations that they want to merge into a shared graph representation for public discourse. A global platform could be scaled up to merge selected parts of conversations from millions of simultaneous conversations with people around the world in real-time. We could have collective intelligence by the end of this year.
21st of December 10:32?
Despite huge AI developments coming out on a regular basis, there are still a bunch of naysayers claiming AI has hit a wall, the bubble will burst, and AGI is decades away.
Wait AI research/development was actually moving? Forwards?! Could've sworn it stopped some 10yrs ago. "AGI is right around the corner! AGI has been around the corner so long, I wonder what it's doing back there?" - Sabine Hossenfelder
It’s bussin no cap
Cosine Genie is awesome - thanks for the review, you're my main source for AI news :)
Do you know any good/decent model for Smart Contracts compiling (& auditing, ideally)? Solidity has a lot in common with JS/TS, so there should be hope
Would love a video about Sakura
How do you check to see if you have access to search GPT?
You'll get an email
Can you make a video on setting up Flux.1 by Blackforestlabs (Set up by founders of Stable Diffusion)?
Been on my list!
Please dedicate a full video review of Sokana's AI Scientist
3:34 that's doraemon. Most famous kid cartoon every created.
cool !! :)
Fun livestream
Do you think that the business model of Open AI is sustainable? I mean how will they make money because there are no ads??
Apple robot arm? Practice on a hotdog first!
Can you make a tutorial on installing Flux on macOS, please?
Google about to be history?! 🙀
Google threatened with breakup just as their core product is made obsolete with searchGPT?
The Apple arm is probably to slap the intruder in the face ("home security applications")...
SearchGPT is incredibly frustrating to use. All those who've actually tested it say so. ATM, it's not ready, and not ready for use.
Ditto Google Gemini (Demo). No points for early release of application that takes three attempts to work. Better to ship an application for production that works as marketed.
More Sakana please!