Thanks for amazing video. I have been building agents for last few weeks. And if anyone is just planning to start building agents here’s my starter kit frameworks - langchain, llamaindex, crewai LLMs - claude, openai & ollama tools - composio memory - mem0, memgpt logging & caching - langsmith, helicone
Maybe the video was initially recorded normally then they flipped it around to making seem like she’s writing back to front. Either that. Or she is just truly skilled at writing backwards👍🏾
HaHa I got freaked out when I first watched www.youtube.com/@NancyPi 's videos, for teaching my kiddo some calculus concepts! Took me a while, but figured out the trick!
It's a good video. I just don't really feel like it's worth my time and effort to create something like that. I am more interested in Biotech.I know that I would be likely to use it and benefit from it, but it's a pea in the pod or 1 small part of a larger entity.
I'm not an IT person by any stretch of the imagination, but I'm encountering this technology more and more in my development of a Media Asset Management system for our non-profit media organization. The software products leveraging AI and agents is exploding into our field of view, and this explanation was very helpful. You're helping me anticipate questions and critiques to apply to vendors offering new products.
AI agents are transforming various industries by automating tasks, enhancing decision-making, and providing personalized experiences. With their ability to analyze vast amounts of data, adapt to new information, and interact with users in natural ways, AI agents are becoming integral to advancing technology and improving efficiency across sectors. As they continue to evolve, their potential to drive innovation and solve complex problems expands, offering exciting opportunities for the future.
It was the best high-level explanation of AI Agents by assign the LLM as incharge, and, also highlighting the programatic approach of Compound AI Systems. And the example which concrete the logic of how AI Agents would be doing the complex tasks.
RPA is very programmatic way, you have to change all base line of robotics to agentic concepts to adapt it. Prolog had modules or routines to integrate programmatic into learning inference process, so RPA outputs might be integrated into AI agents.
I think she is my new/first life coach. She very artfully layed out the comparison between the two operations but also technics i might try myself. Thx!! Very well spoken and great delivery. I'm not an A.I. I just have a lot of projects to do. ;)
Back In My Day We Had A Word For Folks Like You... And Thats A....... U Guess It.... Teachers Pet 📚🪱 My Advice?? Get Ur Head Out Of Those Books For Once Enjoy Ur Life.... Godbless
Absolutely! The focus of multi agent systems will be the major need. Ensuring large context can be narrowed and integrated into systems unlocks so much potential. Our software is solving the problems with multi agent group chat productivity environments and I really believe going from the chainsaw of AI to the scalpel is the future 👌
Fantastic Maya! Your detailed explanation of the shift from monolithic AI models to modular, compound AI systems is enlightening. It's fascinating to see how the integration of LLMs with agent-based systems can enhance adaptability and enable more dynamic interactions across various applications. I'm especially intrigued by the 'ReAct' framework, Combining Reason, Action, and Access memory-as a means to boost AI's adaptability and autonomy. Looking forward to more insights on this topic! With the Rise of AI Agents in 2024, the Age of 'Jarvis' is on the horizon 🤖
Agents would still be bound by the tools that you make them aware of. So essentially, your agent can only do the tasks that you have written the code for (tools). The LLM based agents would exploit their knowledge about the tools and try to connect them all together, that's what the main USP is. Knowing all the available tools and then sticking these tools together in a variety of ways.
But at the end of the day having 800,00+ subscribers split between god who knows how many people just off of buying views is still impressive in itself, not because you earned it but solely because you managed to buy it.
Thank You for the high-level overview! It would be interesting to hear more about tradeoffs between the programmatic and agent approaches (use cases, how agents can be embedded into the existing systems, etc).
I went to school using black boards with chalk. They are quarried from slate carefully mounted to the wall of classrooms. Blackboards got replaced by white dry erase boards. Also used with projectors. Large touch monitors became all the rage. This is my first look at a illuminated rear mirrored clear board. Another cat’s meow…
I really enjoyed Maya Murad. As a female I appreciate female teachers and I think she is a good choice. I would appreciate it if she taught other topics about AI. ^^
Excellent explanation of the next phase of AI development. Never a dull moment these days in the age of AI! I’ve been enjoying IBM courses via Coursera
According to IBM, an artificial intelligence (AI) agent is a system or program capable of autonomously performing tasks on behalf of a user or another system. These agents design their workflows and utilize available tools to achieve their goals. AI agents can handle a wide range of functionalities, including decision-making, problem-solving, interacting with external environments, and executing actions. They are often built on large language models (LLMs) and can adapt to user expectations over time, providing a personalized experience. AI agents are used in various applications, from software design and IT automation to code-generation tools and conversational assistants.
The best advantage of agents is the ability to check and verify each llm output, in addition to querying your leave balance, it can also query your leave entitlement, and how many leave days have been used up, to compare. This will take the accuracy of AI systems from 75% to 99.95%.
What screen, tools, camera, technology and software you are using to record, edit the video? Can you please make video about this. This will help getting answers to all viewers who commented below. Thank you!
AI agents are like digital workers who can think and act alone to help industries with tasks. SmythOS features agents for data analysis, client service, and automating workflows, all handled without coding expertise. Inspiring chances!"
IBM is best at just commentary. No one talks about IBM in the GenAI domain. How could a big company with much resources missed the boat and still unable to catch up?
Very valuable video. I think this topic has potential for another couple videos about how we might implement it (bunch of small distilled slm's like phi-3-128k instead of big ones for ex. to make it runnable on some decent (not necessary macs) laptops). Complex systems relatively new concept but we already have overwhelmingly many platforms. tools and techniques like langchain, graphRAG, beam etc. and another important moment is to find the simple way to compare those complex system for efficiency. Crazy interesting topic, Thank You for your effort. Liked
AI Agent models are broad, complex and yet customizable to the instances, It can retrieve data from our past inputs and give relevant outputs by doing all sorts of thinking, reasoning and iterations.
I learned to write on a blackboard left handed as I lectured. Best way to keep students accountable is to face them. It doesn’t take as long as you think…adults just forgot how much brute force practice you gotta do to learn. Just like when we were kids
Well done and hope Miss Maya will speak at our AI Summit in September for a Fireside discussion at GatherVerse AI Evolve Summit. Well done and thank you.
Whoa, that sounds wonderful to use AI agents to automate monotonous chores like data entry! SmythOS and how it facilitates that form of AI cooperation have always piqued my interest. Having AI do these chores can free up a ton of creative time! #aitools #smythOS
You explained in 12min what would take me 90min! What a great job! This helps sooo much getting people with no background in AI in our companies to understand what the devs are doing and why! thanks a lot!
Thanks for the helpful tip! I tried it out and managed to get 5 out of 5 as well. I'm still in demo mode, but this gives me hope for when I start trading for real
We all know that AI operates on massive amounts of data from the crowd and follows the commands we input. What if we divided the AI's brain mechanism into three main parts: 1. Random real data (instead of waiting for human input), 2. Correcting random data, saving corrections, and looping (similar to the body's immune system remembering how to eliminate pathogens), and 3. Genetic code (the defined behaviors and rules of AI)? For example, humans have different personalities. Some are born perfect, intelligent, and cheerful, while others are aggressive. (To create behaviors that lead to progress and safety, we can remove negative traits, similar to genetic engineering.) For instance, greed leads to decline, aggression and anger lead to violence, and delusion or stupidity hinder progress. In summary, we can remove these three emotions. (Expected outcome) Create errors and successes for AI to learn from various error data through looping, memorization, and self-improvement, similar to human behavior that seeks self-development. In conclusion, to create AI that closely resembles humans, we need to integrate the brain mechanism and the crowd. Comparing the crowd to clear water and the brain mechanism to red color, when we combine them, we get red water. AI brain: Red water.
Do they use transformational grammar to remove the syntactic errors before they are entered into the LLM's? How important is the order of operations for the react configuration. In humans the react configuration is phylogenically ordered, ontogenetically sequenced and functionally progressive. The protocol seems to be the application of the abilities that we aquire at each stage of development in the order they were aquired. Keep in mind A.I. just popped up on my radar recently. Like my nephew says "you're so fossilized."
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?
Thanks for amazing video. I have been building agents for last few weeks. And if anyone is just planning to start building agents here’s my starter kit
frameworks - langchain, llamaindex, crewai
LLMs - claude, openai & ollama
tools - composio
memory - mem0, memgpt
logging & caching - langsmith, helicone
I don't care much about the content but am impressed is how she can write in a backward mirror image. That takes skill !!
Maybe the video was initially recorded normally then they flipped it around to making seem like she’s writing back to front.
Either that. Or she is just truly skilled at writing backwards👍🏾
HaHa I got freaked out when I first watched www.youtube.com/@NancyPi 's videos, for teaching my kiddo some calculus concepts! Took me a while, but figured out the trick!
In reality, she's right handed. Great explanation in simple visuals and words.
are you insane? she is writing from left to right and she is right handed.. Its just the video is being mirrored/flipped :D :Dlol
Glass Lightboard and then flip
This is by far the best explanation of what exactly an AI agent is.
You mean the use of colours ?
@@THC93 makes it more digestable :)
@@THC93 🤣🤣🤣
It's a good video. I just don't really feel like it's worth my time and effort to create something like that. I am more interested in Biotech.I know that I would be likely to use it and benefit from it, but it's a pea in the pod or 1 small part of a larger entity.
Hear hear!
Give this lady a vacation! this is her way of asking it out loud😂
😆
And this has nothing to do with the weather 😅
She wrote everything backwards so she definitely deserves a vacation
😂👌
she's probably an AI agent needing a vacation from all the bogus querying by dumb humans
I'm not an IT person by any stretch of the imagination, but I'm encountering this technology more and more in my development of a Media Asset Management system for our non-profit media organization. The software products leveraging AI and agents is exploding into our field of view, and this explanation was very helpful. You're helping me anticipate questions and critiques to apply to vendors offering new products.
we'll build you that if you want!
I am a Data engineer, let me know if we can do something together
Which technology are you referring to?
What a presentation! Clearly and logically. This girl has large language talent.
IBM Videos are the best. Great way of explaining a complex topic in < 15 minutes.
What an explanation! Kudos for allowing us to think clearly.
Maya, as someone new to this space, your explanation was awesome. Thank You 🙏🏽
Maya does a great job by breaking complex topics into consumable chunks.. Thank you
IBM Technology, thanks for making such videos on topic with easier explanations.
AI agents are transforming various industries by automating tasks, enhancing decision-making, and providing personalized experiences. With their ability to analyze vast amounts of data, adapt to new information, and interact with users in natural ways, AI agents are becoming integral to advancing technology and improving efficiency across sectors. As they continue to evolve, their potential to drive innovation and solve complex problems expands, offering exciting opportunities for the future.
It was the best high-level explanation of AI Agents by assign the LLM as incharge, and, also highlighting the programatic approach of Compound AI Systems. And the example which concrete the logic of how AI Agents would be doing the complex tasks.
Very useful. Thanks! I am doing my PhD research on the possibility of integrating Agentic AI into RPA. It cleared a lot of things to how to tackle it
RPA is very programmatic way, you have to change all base line of robotics to agentic concepts to adapt it. Prolog had modules or routines to integrate programmatic into learning inference process, so RPA outputs might be integrated into AI agents.
the way Aliagents integrates AI with tokenization is changing the game, excited for the future
I think she is my new/first life coach. She very artfully layed out the comparison between the two operations but also technics i might try myself. Thx!! Very well spoken and great delivery.
I'm not an A.I. I just have a lot of projects to do. ;)
Simplest explanation. Every word is understandable. Thank you.
I like the last part when you explained when to use agentic or simple rag approach. Thanks.
Back In My Day We Had A Word For Folks Like You... And Thats A....... U Guess It.... Teachers Pet 📚🪱
My Advice?? Get Ur Head Out Of Those Books For Once Enjoy Ur Life.... Godbless
Glad it was helpful!
Maya is explaining this compound system approach very clearly Thanks Maya
Coumpound system
@@buffhooper7417 "ком-" - комок - комкать (старославянский)😊
You're most welcome
I like the way She explained everything including LLM RAG, Compound AI systems.
Thanks for the video that explains very well what agents are and their evolutions.
Absolutely! The focus of multi agent systems will be the major need.
Ensuring large context can be narrowed and integrated into systems unlocks so much potential.
Our software is solving the problems with multi agent group chat productivity environments and I really believe going from the chainsaw of AI to the scalpel is the future 👌
Fantastic Maya! Your detailed explanation of the shift from monolithic AI models to modular, compound AI systems is enlightening. It's fascinating to see how the integration of LLMs with agent-based systems can enhance adaptability and enable more dynamic interactions across various applications. I'm especially intrigued by the 'ReAct' framework, Combining Reason, Action, and Access memory-as a means to boost AI's adaptability and autonomy. Looking forward to more insights on this topic!
With the Rise of AI Agents in 2024, the Age of 'Jarvis' is on the horizon 🤖
I asked these questions to myself two-three days ago and, by surprise, I was able to answer them by myself as well.
IBM's project manager has this level of expertise, impressive!
*Product* Manager - big difference!
@@tatvafnu6604😂Yh people don’t know the difference
very clear presentation on the Agentic vs programatic approach. Love it !
Agents would still be bound by the tools that you make them aware of. So essentially, your agent can only do the tasks that you have written the code for (tools). The LLM based agents would exploit their knowledge about the tools and try to connect them all together, that's what the main USP is. Knowing all the available tools and then sticking these tools together in a variety of ways.
You explained this the most difficult way you could’ve good job
But at the end of the day having 800,00+ subscribers split between god who knows how many people just off of buying views is still impressive in itself, not because you earned it but solely because you managed to buy it.
@@dylanruss1135are you ok
IBM always dropping A+ content, thankss
I Can't agree more, the explanation was amazing, the didatics was awesome!!! Congrats!!
One of the best explanations ever seen in internet.. Thank you so much for taking your time
Thank You for the high-level overview!
It would be interesting to hear more about tradeoffs between the programmatic and agent approaches (use cases, how agents can be embedded into the existing systems, etc).
I went to school using black boards with chalk. They are quarried from slate carefully mounted to the wall of classrooms.
Blackboards got replaced by white dry erase boards. Also used with projectors.
Large touch monitors became all the rage.
This is my first look at a illuminated rear mirrored clear board. Another cat’s meow…
Thank you, Great tutorial!!!
Such a profound and insightful video on the internet is available.
Great job with explaining this. Probably the best explanation I have heard.
Good presentation… easy to follow and understand. I intuitively understood as she gave examples that my experience reinforced.
Thank you 😊
Thanks for sharing!
Extremely educational---this IBM channel is really really good--thank you!!! ❤ 🧡 💛 💚 💙 💜
Our pleasure!
Wow, she was really great at explaining the concept! Now it makes sense. Would be great to have a simulated version of this person as a teacher! :D
How do you know she's not ?
These IBM videos always explains the concepts clearly.
Remarkable clarity, excellent explanation!!
Great explanation of AI Agents! I love working with them and seeing them reason issues.
Gosh as a small business owner we are going through over worst time of the year…And she is teaching us happiness ! That how it works in TH-cam…😅
Crisp. On-point. Well executed. Kudos to you and your team !
Thanks a ton
Stephan, thanks for the presentation. Very nice talk.
Glad you liked it!
I really enjoyed Maya Murad. As a female I appreciate female teachers and I think she is a good choice. I would appreciate it if she taught other topics about AI. ^^
Thanks for sharing!
Excellent explanation of the next phase of AI development. Never a dull moment these days in the age of AI! I’ve been enjoying IBM courses via Coursera
According to IBM, an artificial intelligence (AI) agent is a system or program capable of autonomously performing tasks on behalf of a user or another system. These agents design their workflows and utilize available tools to achieve their goals. AI agents can handle a wide range of functionalities, including decision-making, problem-solving, interacting with external environments, and executing actions.
They are often built on large language models (LLMs) and can adapt to user expectations over time, providing a personalized experience. AI agents are used in various applications, from software design and IT automation to code-generation tools and conversational assistants.
ur positive energy is contagious and your videos always brighten up my day, thank you!!! 😉
The best advantage of agents is the ability to check and verify each llm output, in addition to querying your leave balance, it can also query your leave entitlement, and how many leave days have been used up, to compare. This will take the accuracy of AI systems from 75% to 99.95%.
What screen, tools, camera, technology and software you are using to record, edit the video? Can you please make video about this. This will help getting answers to all viewers who commented below.
Thank you!
Awesome information & superb lecture!!! Spot on!!!
Glad you enjoyed it!
@@IBMTechnology of course!!
Nice overall picture of how AI agents are evolving.
This is really excellent.
AI agents are like digital workers who can think and act alone to help industries with tasks. SmythOS features agents for data analysis, client service, and automating workflows, all handled without coding expertise. Inspiring chances!"
IBM is best at just commentary. No one talks about IBM in the GenAI domain. How could a big company with much resources missed the boat and still unable to catch up?
Very valuable video. I think this topic has potential for another couple videos about how we might implement it (bunch of small distilled slm's like phi-3-128k instead of big ones for ex. to make it runnable on some decent (not necessary macs) laptops). Complex systems relatively new concept but we already have overwhelmingly many platforms. tools and techniques like langchain, graphRAG, beam etc. and another important moment is to find the simple way to compare those complex system for efficiency. Crazy interesting topic, Thank You for your effort. Liked
AI Agent models are broad, complex and yet customizable to the instances, It can retrieve data from our past inputs and give relevant outputs by doing all sorts of thinking, reasoning and iterations.
Give this woman an award for WRITING BACKWARDS WITH NO HESITATION!!! 🏆 (unless she’s AI-generated…)
Very good explanation! The best so fat from you guys!!❤
Great explaination for agents! Helpful! Thank you
How long until AI agents are good enough for IBM consulting to turn a profit?
I learned to write on a blackboard left handed as I lectured. Best way to keep students accountable is to face them. It doesn’t take as long as you think…adults just forgot how much brute force practice you gotta do to learn. Just like when we were kids
Well done and hope Miss Maya will speak at our AI Summit in September for a Fireside discussion at GatherVerse AI Evolve Summit. Well done and thank you.
Writing in reverse must be difficult. Kudos for clear explanations despite writing this way.
for narrator : Start teaching these concepts along your job, you have a hidden talent : teaching
excellent overview, thank you.
How do u benchmark performance ? Seems like probability of errors can go up too. Ref for such research? Thx u.
Thank you so much for this. This will help me in my project
Such an informative video!
Whoa, that sounds wonderful to use AI agents to automate monotonous chores like data entry! SmythOS and how it facilitates that form of AI cooperation have always piqued my interest. Having AI do these chores can free up a ton of creative time! #aitools #smythOS
Thank you! Best explanation so far!
Glad it was helpful!
Лаба, твои инсайды просто бомба! Жду новых идей.
You explained in 12min what would take me 90min! What a great job! This helps sooo much getting people with no background in AI in our companies to understand what the devs are doing and why! thanks a lot!
Glad it was helpful!
Thanks for the helpful tip! I tried it out and managed to get 5 out of 5 as well. I'm still in demo mode, but this gives me hope for when I start trading for real
You got this!
She's not writing backwards it's AI doing that! 😊
Heel goed uitgelegd; beste presentatie over Agentic systems tot nu toe. E nu het vervolg. Hoe maak je een agentic system?
great explanation!! Keep it going!!
Great topic and very well presented! Thank you!
Excellent presentation, Maya. Thank you for explaining this concept so well. Have fun on your vacation!
This was actually very useful.
Brilliant explanation
1. When will this be available? 2. Are there any UI demos?
See Wargames starring Matthew Broderick.
Thank you for an excellent lecture.
This was a really helpful video for me. These IBM videos have really great content.
Glad you like them!
A+ Presentation. Thanks!
Very good. Thanks.
We all know that AI operates on massive amounts of data from the crowd and follows the commands we input. What if we divided the AI's brain mechanism into three main parts: 1. Random real data (instead of waiting for human input), 2. Correcting random data, saving corrections, and looping (similar to the body's immune system remembering how to eliminate pathogens), and 3. Genetic code (the defined behaviors and rules of AI)?
For example, humans have different personalities. Some are born perfect, intelligent, and cheerful, while others are aggressive. (To create behaviors that lead to progress and safety, we can remove negative traits, similar to genetic engineering.) For instance, greed leads to decline, aggression and anger lead to violence, and delusion or stupidity hinder progress. In summary, we can remove these three emotions.
(Expected outcome)
Create errors and successes for AI to learn from various error data through looping, memorization, and self-improvement, similar to human behavior that seeks self-development.
In conclusion, to create AI that closely resembles humans, we need to integrate the brain mechanism and the crowd. Comparing the crowd to clear water and the brain mechanism to red color, when we combine them, we get red water.
AI brain: Red water.
Excellent info! Thank you. 🙏
Glad you enjoyed it!
Very clearly explained and informative.
Now I understand my mental burnout!! Im constantly mentally working my agent mind and looping!!😂
Great explanation. 1 question, how to set the control logic?
Great overview, this is iconic
Do they use transformational grammar to remove the syntactic errors before they are entered into the LLM's? How important is the order of operations for the react configuration. In humans the react configuration is phylogenically ordered, ontogenetically sequenced and functionally progressive. The protocol seems to be the application of the abilities that we aquire at each stage of development in the order they were aquired. Keep in mind A.I. just popped up on my radar recently. Like my nephew says "you're so fossilized."
Excellent explanation by Maya! 👏🙌
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?
What kind of a glass white board is used here? Excellent video 👍🏼
Thank you! Cheers!
very well done, thanks
This mental model of agents and LLMs is brilliant.
Maya is so good looking and so smart. Brilliant!