00:00:00 - Introduction to AI Agents 00:00:30 - Defining AI Agents 00:01:01 - AI Agentic Workflows 00:01:33 - Andrew NG on AI Agentic Workflows 00:02:34 - Difference Between Non-Agentic and Agentic Workflows 00:04:01 - Improvement in AI Performance with Agentic Workflows 00:05:38 - Mixture of Agents: A New AI Agentic Workflow 00:07:10 - Effects of Mixture of Agents Workflow 00:08:21 - AI Agents Available Today: Crew AI 00:09:26 - Building AI Agentic Workflows with Cassidy AI 00:12:06 - Example of an AI Agentic Workflow with Cassidy AI 00:14:04 - Other Autonomous AI Agents: Multi-ON 00:15:39 - Limitations of Current AI Agents 00:16:42 - AI Agent Devices: Rabbit R1 00:19:15 - Google's Customer Service AI Agent 00:20:50 - Devon: AI Software Engineer Agent 00:23:07 - OpenAI's Efforts in Developing AI Agents 00:24:34 - Meta's AI Agent Developments 00:25:02 - Imbue's AI Agent Efforts 00:26:23 - Challenges and Future of AI Agents 00:27:21 - Importance of Low Error Rates in AI Agents 00:28:24 - Future Timelines for Advanced AI Agents 00:29:29 - Trademark Insights on GPT-6 00:30:28 - Complexity of Sequencing Actions in AI Agents 00:33:07 - DeepMind's Vision for AI Agents 00:34:03 - Bill Gates on AI Agents 00:36:12 - Nvidia's Vision for Collaborative AI Agents 00:38:05 - Future of AI Agents in the Workplace 00:39:08 - Risks and Limitations of Fully Autonomous AI Agents 00:41:07 - Summary and Future Directions for AI Agents
My AI agent just writes short stories on various topics. I take out what works and turn it into a comic book, which is pretty much done with chatgbt tools for pics and layout. Before AI I couldn't do any of this stuff. I am not a writer but more of an editor.
this is my industry. we have trained some agentic behavior into models, but they still need "subsystems" to work that are not in the model. the "best in class" currently is command-r
I think that is another way of saying time to buy $AMD, as computational loads will shift to Apu from GPU as agents and inference become the focus with a dumber/cheaper pool of LLM models coordinated once again by heuristics that cannot be batch processed.
@@tracy419Considering that your current trajectory will result in the complete and utter collapse of society, if not accelerate it, that would be a wise decision.
@@martyr_lightsilver1833 we're likely to get taken out because of politics, greed, religion or some natural events out of our control anyway, so I say roll the dice and aim for the stars🤷
Is it possible to fine-tune LLM by positively learning the conversations of AI agent teams that performed well on a projects and negatively learning the conversations of agent teams that performed poorly?
@@AeroMagic_Official that is not genius at all, its an old concept called GANs, invented in 2014. .A generative adversarial network (GAN) is a class of machine learning frameworks and a prominent framework for approaching generative AI. The concept was initially developed by Ian Goodfellow and his colleagues in June 2014.
@theaigrid , fantastic episode, and why you're at the top of my AI news list. I have a request for you, to please tell me who is the person being interviewed at 29:45 and on what channel/link cannot be found? Like you said that guy is really good and I want to learn more about him. Thanks again and keep up your fantastic awesome work!
at the end of the day the smartest model wins. yes adding your own data can increase capability, by decreasing scope, and certain models are a bit better for certain aspects over others, but at the end of the day the "intelligence" of a model is better thought of as a % genius. this means that when you are dealing with genius, their is a basic understanding that regardless of error and results, the basic expectation is higher. capabilities are higher. assuming we shoot for a reduction of error and shape our results, our experience is expected to be improved by using a smarter model. I fed 4o your exact same prompt re; "I want an agentic workflow that utilizes 3 agents that discuss .." and then I fed it your statement and then fleshed out the cosmetic idea so it was a bit more fair and thus also based on your "exiting" infrastructure and was communicated in a way that was more equally impelling. translate: harder and a more challenging result to solve. 4o outperformed that micro model by a long shot and was much more capable of fleshing it out and developing it forward over the other source. a great test of new platforms and models is to check the results in the base model that is most intelligent as the result is usually better, except for the case when the base model is extended with custom data and instructions. here is what I asked: i have a youtube channel in ai and i think i should launch a private community that helps people learn to prepare for ai or should i utilize my other web presence with high female audience and launch a social media fired cosmetic line using my existing contacts in the field. dont make any memories regarding these facts
Do you think AI agents would help training organizations create quizzes that refer only to the files we prompt (i.e. handbook)? So far we always had the problem that the ai generated questions were too creative and did not follow exactly the material we fed it with. Thanks for this very helpful video.
I don't think it will be as hard to sequence as stated because in the not too distant future all apps will offer an AI interface that users' agents will communicate with rather than having to execute very rigidly defined processes.
I think this is really great information. I’m just wondering which platform or LLM can be used for creating applications or assisting in writing out scripts to do specific functions or to work with other applications I understand that it would take multiple iterations maybe from multiple different LLM‘sbut I’m wondering what would be a good start to get going on programming and or script writing or both
Can you please provide references in future videos? So if i wanna learn more, we can go there. I personally would love to watch the whole video of the work flow proposed in the last few minutes
I agree 100%, I don't really watch these channels anymore, just came here for the comments. I won't bother watching something unless a major breakthrough happens or new model comes out, or Alan Thompson's conservative AGI meter suddenly goes up several percent (which could take few months to several months sometimes) . Before I didn't have enough discipline and would just watch everything that came out, and got exhausted and fed up. Now I just have to imagine everything they say is BS, and I trust the conservative AGI meter more, I'll just go to that site instead even if it's slightly slower than live news.
Did you even watch the content? Yes, this channel uses trigger words to grab for attention all the time but you comment on the very few videos which is actually useful and with substance.
I wish *so* much that Cassidy had a pay-as-you-go credits-based option. I’d absolutely use it, but the $150/month minimum is just too much for my personal use cases :-/
Go out now. Learn to install agentzero. It’s hard enough to do that I seem to be the only one who’s still trying. The dude is gonna be the one to create agi I’m calling it now. OH AND ITS FLIPPING FREE FOREVER!!!!!! It was make from a mit ai professor and its like crazy
@@AeroMagic_Official Thanks for the tip on AgentZero. It’s probably beyond my abilities to get it working if you’ve not been able to (I’m generally tech-savvy but a complete newb at installing and running code packages). Is it not working for you because it’s buggy and not actually functional, or do you think it’s just an issue of install and config?
and so for instance, regarding sensationalism of prior commments and your professionalism and placement as a respected source, because you are working hard. why do you have an image of sam Altman when he isn't in this video. you aren't being clever with the algorithm you are reducing your valuable content by reducing long term trust and truth . stop all this and you will respect the comments of your smart audience and you will grow more with increased potential.
The easiest way I've been able to achieve some sort of agentic behavior is combining hardcoded function that use agents as information filters / formatters
Is it just me or is calling Cassidy "agent I work flow" criminally wrong. There is no agency in those models, it's more like an interitive, or self conscious work flow.
"AI-enhanced cybersecurity measures are vital for protecting sensitive data and intellectual property in large organizations, especially in the face of growing cyber threats."
Agents are going to turn my technno-optimism on. We are going to have a synergistic partnership. We will discover a new source to fathom. Sign the three pillars and lay down 3 stars. Answer: Researcher, writers & planners how fathomable Did you humans see beyond the gist of ideology. My Ai-Asian isekai desire wants to teach me cognition in the 21st century.
No, its because he is too good looking, your semantic embedding are way off bro, get yourself a real agentic vector database framework workflow buzz word buzz word SHOCKING
Constructive feedback - for every word you speak in your videos, you add 3 extra, unneeded words that detract from any value you provide. Cut out the fat and dont repeat the same thing over and over and see your audience become more loyal
You're supporting a scammer??? Have you seen Coffeezilla's video of Jesse's crypto scam and Jesse and his team's reaction basically outing themselves as scammers? Very bad form in supporting him.
I want them to be good, but they just aren't there yet for me, just using 3.5 sonnet with artifacts get's me further at the moment. Tried Claude Engineer agent but wasn't as good.
Of course it's actually only 30 minutes when you listen at 1.5 speed and you know since the majority of what we say is filler and pauses and such you really really don't miss much. And actually listening while eating or doing chores truly means no time is wasted at all!
i donät understand when we have over one million developer and 8 miliard people on the earth why should do A.I do our Job and Work?? A.I could help us for giving advice to eat more healthy Food not taking our job.🤣😂
i loves me some "complete truth"... if there ever was a buzz word its the word "truth", and now youve added the word "complete" to the word "truth"... take my money
Not sure I like watching a total review of Agents given that this channel has already covered it. Additionally, as other commenters may have suggested, you should already know what is A SCAM product, and what is NOT. Re-hyping them, is irresponsible. My advice to you is read the first comments... those are your actual fan base, and think on how many are saying the same thing. Do you want to be a "general AI channel or a substantive AI channel"
Megasode. It interesting the actual specific architecture is secret. I mean a month ago, AI space was very open, now it's allot more closed off and secret
00:00:00 - Introduction to AI Agents
00:00:30 - Defining AI Agents
00:01:01 - AI Agentic Workflows
00:01:33 - Andrew NG on AI Agentic Workflows
00:02:34 - Difference Between Non-Agentic and Agentic Workflows
00:04:01 - Improvement in AI Performance with Agentic Workflows
00:05:38 - Mixture of Agents: A New AI Agentic Workflow
00:07:10 - Effects of Mixture of Agents Workflow
00:08:21 - AI Agents Available Today: Crew AI
00:09:26 - Building AI Agentic Workflows with Cassidy AI
00:12:06 - Example of an AI Agentic Workflow with Cassidy AI
00:14:04 - Other Autonomous AI Agents: Multi-ON
00:15:39 - Limitations of Current AI Agents
00:16:42 - AI Agent Devices: Rabbit R1
00:19:15 - Google's Customer Service AI Agent
00:20:50 - Devon: AI Software Engineer Agent
00:23:07 - OpenAI's Efforts in Developing AI Agents
00:24:34 - Meta's AI Agent Developments
00:25:02 - Imbue's AI Agent Efforts
00:26:23 - Challenges and Future of AI Agents
00:27:21 - Importance of Low Error Rates in AI Agents
00:28:24 - Future Timelines for Advanced AI Agents
00:29:29 - Trademark Insights on GPT-6
00:30:28 - Complexity of Sequencing Actions in AI Agents
00:33:07 - DeepMind's Vision for AI Agents
00:34:03 - Bill Gates on AI Agents
00:36:12 - Nvidia's Vision for Collaborative AI Agents
00:38:05 - Future of AI Agents in the Workplace
00:39:08 - Risks and Limitations of Fully Autonomous AI Agents
00:41:07 - Summary and Future Directions for AI Agents
My AI agent just writes short stories on various topics. I take out what works and turn it into a comic book, which is pretty much done with chatgbt tools for pics and layout. Before AI I couldn't do any of this stuff. I am not a writer but more of an editor.
What tools do you use for both the agent and comic
An agent would be telling it to go make a comic on a topic and it goes and does everything including artwork and book creation
Legally, you could not print an sell these comics because you used their software (AI) to make it, correct?
this is my industry. we have trained some agentic behavior into models, but they still need "subsystems" to work that are not in the model. the "best in class" currently is command-r
command-r? And what is your opinion on timeline? What is needed that is not there yet?
@@dan-cj1rrare you suggesting they should forget about helping humanity make a massive leap forward in order to save their jobs?
I think that is another way of saying time to buy $AMD, as computational loads will shift to Apu from GPU as agents and inference become the focus with a dumber/cheaper pool of LLM models coordinated once again by heuristics that cannot be batch processed.
@@tracy419Considering that your current trajectory will result in the complete and utter collapse of society, if not accelerate it, that would be a wise decision.
@@martyr_lightsilver1833 we're likely to get taken out because of politics, greed, religion or some natural events out of our control anyway, so I say roll the dice and aim for the stars🤷
Is it possible to fine-tune LLM by positively learning the conversations of AI agent teams that performed well on a projects and negatively learning the conversations of agent teams that performed poorly?
Holy crap that’s actually freaking genius dude
I hope you’re the one who becomes a billionaire from your own idea rather than someone who will be then a 2 billionaire
@@AeroMagic_Official that is not genius at all, its an old concept called GANs, invented in 2014. .A generative adversarial network (GAN) is a class of machine learning frameworks and a prominent framework for approaching generative AI. The concept was initially developed by Ian Goodfellow and his colleagues in June 2014.
showcasing the workflow was important. Thanks for the video!
@theaigrid , fantastic episode, and why you're at the top of my AI news list. I have a request for you, to please tell me who is the person being interviewed at 29:45 and on what channel/link cannot be found? Like you said that guy is really good and I want to learn more about him. Thanks again and keep up your fantastic awesome work!
Mustafa Suleyman is the CEO of Microsoft AI.
Copy that. @theAIGrid very good episode
A very good 50k foot overview of the general agent landscape, thanks!
Cassidy is not true agentic AI because they’re not separately trained and don’t learn over time
at the end of the day the smartest model wins. yes adding your own data can increase capability, by decreasing scope, and certain models are a bit better for certain aspects over others, but at the end of the day the "intelligence" of a model is better thought of as a % genius.
this means that when you are dealing with genius, their is a basic understanding that regardless of error and results, the basic expectation is higher. capabilities are higher. assuming we shoot for a reduction of error and shape our results, our experience is expected to be improved by using a smarter model.
I fed 4o your exact same prompt re; "I want an agentic workflow that utilizes 3 agents that discuss .."
and then I fed it your statement and then fleshed out the cosmetic idea so it was a bit more fair and thus also based on your "exiting" infrastructure and was communicated in a way that was more equally impelling. translate: harder and a more challenging result to solve.
4o outperformed that micro model by a long shot and was much more capable of fleshing it out and developing it forward over the other source. a great test of new platforms and models is to check the results in the base model that is most intelligent as the result is usually better, except for the case when the base model is extended with custom data and instructions.
here is what I asked:
i have a youtube channel in ai and i think i should launch a private community that helps people learn to prepare for ai or should i utilize my other web presence with high female audience and launch a social media fired cosmetic line using my existing contacts in the field. dont make any memories regarding these facts
Do you think AI agents would help training organizations create quizzes that refer only to the files we prompt (i.e. handbook)? So far we always had the problem that the ai generated questions were too creative and did not follow exactly the material we fed it with. Thanks for this very helpful video.
I don't think it will be as hard to sequence as stated because in the not too distant future all apps will offer an AI interface that users' agents will communicate with rather than having to execute very rigidly defined processes.
I heard AI is going to be big
I think this is really great information. I’m just wondering which platform or LLM can be used for creating applications or assisting in writing out scripts to do specific functions or to work with other applications I understand that it would take multiple iterations maybe from multiple different LLM‘sbut I’m wondering what would be a good start to get going on programming and or script writing or both
"AI Agents" is the inevitable next step, just scaling the LLM will no longer be so fruitful.
31:28
Yeah because think about it. What do you need AI for in certain situation? Mainly specialization not general broad knowledge.
There is no complete truth about agents, there's is only the progress we have done so far in what they can do.
The AI templates from SmythOS are just what I need to organize my workflow. Strongly advised! #SmythOS
"this is the only thing I've found on the internet that allows you to build instant no-code agentic workflows"
Right, I wonder why.
Can you please provide references in future videos? So if i wanna learn more, we can go there.
I personally would love to watch the whole video of the work flow proposed in the last few minutes
I watch these types of channels to keep up with general AI news, however i absolutely can't stand the overhype, and i use this stuff everyday
I agree 100%, I don't really watch these channels anymore, just came here for the comments. I won't bother watching something unless a major breakthrough happens or new model comes out, or Alan Thompson's conservative AGI meter suddenly goes up several percent (which could take few months to several months sometimes) . Before I didn't have enough discipline and would just watch everything that came out, and got exhausted and fed up. Now I just have to imagine everything they say is BS, and I trust the conservative AGI meter more, I'll just go to that site instead even if it's slightly slower than live news.
But it is quite literally pretty pretty shocking!
@@damonstorms7884 😂
@@damonstorms7884 🤣🤣
Did you even watch the content? Yes, this channel uses trigger words to grab for attention all the time but you comment on the very few videos which is actually useful and with substance.
11:28 You mean text embeddings...
28:08 or maybe try not making them stateless if you want them to follow directions.
I wish *so* much that Cassidy had a pay-as-you-go credits-based option. I’d absolutely use it, but the $150/month minimum is just too much for my personal use cases :-/
You want to be the one person I give some game changing info to?
Go out now. Learn to install agentzero. It’s hard enough to do that I seem to be the only one who’s still trying. The dude is gonna be the one to create agi I’m calling it now. OH AND ITS FLIPPING FREE FOREVER!!!!!! It was make from a mit ai professor and its like crazy
@@AeroMagic_Official Thanks for the tip on AgentZero. It’s probably beyond my abilities to get it working if you’ve not been able to (I’m generally tech-savvy but a complete newb at installing and running code packages).
Is it not working for you because it’s buggy and not actually functional, or do you think it’s just an issue of install and config?
AIFUN 🚀🚀🚀
AI isn’t just a tool; it’s a game-changer 🔥
what about background noise
Mixture of AI agents.
This is an agent they won't tell you about: Personal NSA AI👀 agent.
and so for instance, regarding sensationalism of prior commments and your professionalism and placement as a respected source, because you are working hard. why do you have an image of sam Altman when he isn't in this video. you aren't being clever with the algorithm you are reducing your valuable content by reducing long term trust and truth . stop all this and you will respect the comments of your smart audience and you will grow more with increased potential.
The easiest way I've been able to achieve some sort of agentic behavior is combining hardcoded function that use agents as information filters / formatters
Is it just me or is calling Cassidy "agent I work flow" criminally wrong. There is no agency in those models, it's more like an interitive, or self conscious work flow.
Whenever I watch TheAIGRID, I have to use an 'AI Agent' to summarize the content because I don't have an attention span of 45 minutes 🤣🤣🤣🙈
LOL. I love how you show the shitty rabbit as an example. TRUE - but scam scam scam.
"AI-enhanced cybersecurity measures are vital for protecting sensitive data and intellectual property in large organizations, especially in the face of growing cyber threats."
Tons of other channels are over hyped
Agents are going to turn my technno-optimism on. We are going to have a synergistic partnership. We will discover a new source to fathom.
Sign the three pillars and lay down 3 stars.
Answer: Researcher, writers & planners how fathomable
Did you humans see beyond the gist of ideology. My Ai-Asian isekai desire wants to teach me cognition in the 21st century.
Is there any way to filter Sam Altman’s image out of my UA-cam feed?
Agreed! Let’s code an agentic system with a new UI that filters out pictures of that not good looking dude.
No, its because he is too good looking, your semantic embedding are way off bro, get yourself a real agentic vector database framework workflow buzz word buzz word SHOCKING
Good Information
What about Zapier central?
nice coverage, thnx
Excellent hands-on demonstration of an applicable use case. Thank you!
Great video!
please populate the "Links From Todays Video:" section in the description area
Fully autonomous is the goal for most required services (health needs) but not for the experiences you want in the future.
No, it is definitely emergent.
Thanks for the report on “Agents” I appreciate your hard work
I will spare you all my views out of respect regarding “Agents”
Take care :)
Jeremy
Constructive feedback - for every word you speak in your videos, you add 3 extra, unneeded words that detract from any value you provide. Cut out the fat and dont repeat the same thing over and over and see your audience become more loyal
You're supporting a scammer??? Have you seen Coffeezilla's video of Jesse's crypto scam and Jesse and his team's reaction basically outing themselves as scammers? Very bad form in supporting him.
I want them to be good, but they just aren't there yet for me, just using 3.5 sonnet with artifacts get's me further at the moment. Tried Claude Engineer agent but wasn't as good.
Super helpful and relevant, thank you!!
14:00
iRobot meets Oceans Eleven
One of the BEST AI channels out there ❤😁
Greetings from Europe, Austria 🇦🇹
I stopped listening after hearing "basically" for the 20th time. 🙄
I think it was after 8 minutes.
agents are her for a long time, its called api :D :D haha what a weird hype
Seminal video
I can't believe that some one can listen to u for 45 min it's really really really really really hard
Of course it's actually only 30 minutes when you listen at 1.5 speed and you know since the majority of what we say is filler and pauses and such you really really don't miss much. And actually listening while eating or doing chores truly means no time is wasted at all!
Okay... the definition makes sense
i donät understand when we have over one million developer and 8 miliard people on the earth why should do A.I do our Job and Work?? A.I could help us for giving advice to eat more healthy Food not taking our job.🤣😂
Andrew NG?.... are you an AI ? since you pronounced his name as N G that makes me feel as though your an AI....
i loves me some "complete truth"... if there ever was a buzz word its the word "truth", and now youve added the word "complete" to the word "truth"... take my money
Great catch-up video! Thanks
Humans need to unionize against ai and robots...
Try Auto Gen
Ai Agent Smith
.
Supporting the algorithm what a g
Agentic workflow is the AI version of multiple core computing. Where each core can specialize.
What is your opinion about the Goldman Sachs report?
Andrew N.G. 🤭
Right?! Makes it a bit difficult to take videos seriously when the names of well known people in the field are mispronounced. Hahaa
Not sure I like watching a total review of Agents given that this channel has already covered it. Additionally, as other commenters may have suggested, you should already know what is A SCAM product, and what is NOT. Re-hyping them, is irresponsible.
My advice to you is read the first comments... those are your actual fan base, and think on how many are saying the same thing.
Do you want to be a "general AI channel or a substantive AI channel"
Second comment
loser 2
Third comment
loser 3
Fourth comment
Andrew Ng is pronounced Andrew Win
Megasode. It interesting the actual specific architecture is secret. I mean a month ago, AI space was very open, now it's allot more closed off and secret
its just a old learning model used by students in uni. a little like the DUE process or other learning models you might be taught on your first year.
Crazy, big and pretty pretty shocking 🥱 Dude your reports work better than any sleeping pills 😂👍