The COMPLETE TRUTH About AI Agents (2024)

Prepare For AGI With me - www.skool.com/postagiprepardness
🐤 Follow Me on Twitter / theaigrid
🌐 Checkout My website - theaigrid.com/
00:00 - Intro to AI agents
01:21 - Generic agent workflows explained
03:06 - Generic workflows for complex tasks
04:08 - Generic workflows improve GPT-3.5 & GPT-4
05:10 - Mixture of agents paper examples
08:13 - Open-source LLMs beat GPT-4 with mixture of agents
09:16 - Few real-world agent use cases currently
09:46 - No-code agent workflow demo in Cassidy AI
13:54 - Multi-On web browsing agent overview
16:27 - Rabbit AI device agent & early issues
19:22 - Google customer service agent demo
21:14 - Devin AI coding agent from Cognition Labs
22:20 - OpenAI agent to control user's computer
23:32 - Meta's engineering & monetization agents
24:59 - IMVU's reasoning-based coding agents
26:26 - Challenges making reliable real-world agents
29:38 - Hard for agents to do multi-step tasks with few errors
32:45 - Google: 1-2 years to multi-modal AI assistants
34:26 - Bill Gates on very knowledgeable AI agents
36:18 - Nvidia CEO on future AI agent teams in business
39:07 - Risks of fully autonomous AI agents
41:01 - Key agent parts: tools, memory, planning, actions
42:27 - Better language models vs prompts to improve agents
43:48 - User interface design key for agent workflows
44:13 - New agent workflows for coding tasks
Links From Todays Video:
Welcome to my channel where i bring you the latest breakthroughs in AI. From deep learning to robotics, i cover it all. My videos offer valuable insights and perspectives that will expand your knowledge and understanding of this rapidly evolving field. Be sure to subscribe and stay updated on my latest videos.
Was there anything i missed?
(For Business Enquiries) [e-mail]
#LLM #Largelanguagemodel #chatgpt
#AI
#ArtificialIntelligence
#MachineLearning
#DeepLearning
#NeuralNetworks
#Robotics
#DataScience

[@MrNezlee]

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?

[@DaveEtchells]

A very good 50k foot overview of the general agent landscape, thanks!

[@DaveEtchells]

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 :-/

[@ariisaac5111]

@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!

[@oshodikolapo2159]

Mustafa Suleyman is the CEO of Microsoft AI.

[@TrustEnabler]

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.

[@Gigi-zy1kx]

I heard AI is going to be big

[@user-qg8qc5qb9r]

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

[@user-iz1kn3ti6d]

What about Zapier central?

[@agenticmark]

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

[@renman3000]

command-r? And what is your opinion on timeline? What is needed that is not there yet?

[@dan-cj1rr]

yea thats cringe imagine trying to automate yourself

[@tracy419]

​@@dan-cj1rrare you suggesting they should forget about helping humanity make a massive leap forward in order to save their jobs?

[@dan-cj1rr]

@@tracy419 if you think turning humans into useless people with no purpose is a leap yea sure. Human are not made to just stay home and do nothing and get depressed.

[@ariisaac5111]

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.

[@gscott48]

Great video!

[@rjackstheartofwealth6152]

Cassidy is not true agentic AI because they’re not separately trained and don’t learn over time

[@ebutuoyjg]

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

[@tristanotear3059]

Is there any way to filter Sam Altman’s image out of my KZbin feed?

[@orthodox_gentleman]

Agreed! Let’s code an agentic system with a new UI that filters out pictures of that not good looking dude.

[@Highdealist]

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

[@user-td4pf6rr2t]

11:28 You mean text embeddings... 28:08 or maybe try not making them stateless if you want them to follow directions.

[@bitcode_]

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

[@phen-themoogle7651]

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.

[@damonstorms7884]

But it is quite literally pretty pretty shocking!

[@bitcode_]

@@damonstorms7884 😂

[@zorororonoa2469]

@@damonstorms7884 🤣🤣

[@aalluubbaa]

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.

[@AngeloXification]

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

[@softwareEngineerGuy]

please populate the "Links From Todays Video:" section in the description area

[@VvbbBb-pj7wq]

14:00

[@liamcoates4890]

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.

[@user-zs8lp3lg3j]

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.

[@mrbladabla]

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.

[@youdontneedmyrealname]

Fully autonomous is the goal for most required services (health needs) but not for the experiences you want in the future.

[@jasonk125]

Shopping and booking flights. Such an incredible lack of imagination at so many companies. Reminds me of when the IBM PC first came out and there was advert after advert about storing your recipes... like really? a $2000 recipe box?

[@stephanie2533]

Super helpful and relevant, thank you!!

[@Copa20777]

Okay... the definition makes sense

[@ebutuoyjg]

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.

[@Techsmartreviews]

Excellent hands-on demonstration of an applicable use case. Thank you!

[@neomatrix2669]

"AI Agents" is the inevitable next step, just scaling the LLM will no longer be so fruitful.

[@thymenwestrum7011]

31:28

[@LiquidAIWater]

Yeah because think about it. What do you need AI for in certain situation? Mainly specialization not general broad knowledge.

[@claudiaweisz8129]

One of the BEST AI channels out there ❤😁 Greetings from Europe, Austria 🇦🇹

[@Jeremy-Ai]

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

[@angloland4539]

[@Ali-behdar]

I can't believe that some one can listen to u for 45 min it's really really really really really hard

[@KunDee-ch5jq]

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!

[@pedrorafaelnunes]

Try Auto Gen

[@SpiritualConduit]

Ai Agent Smith

[@ismaelplaca244]

Dud the Rabbit was a scam and a sham do your research

[@LiquidAIWater]

"don't blame me but the rabbit done died"- Aerosmith 🤣

[@Highdealist]

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

[@sagarvarade]

.

[@thymenwestrum7011]

Supporting the algorithm what a g

[@MrJoeymartinns]

Andrew N.G. 🤭

[@dwjx71]

Right?! Makes it a bit difficult to take videos seriously when the names of well known people in the field are mispronounced. Hahaa

[@svenhoek]

What is your opinion about the Goldman Sachs report?

[@eddielee3928]

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.

[@TheMrCougarful]

Agentic workflow is the AI version of multiple core computing. Where each core can specialize.

[@CliMzOuu]

Great catch-up video! Thanks

[@DJWESG1]

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

[@marcfruchtman9473]

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"

[@ismaelplaca244]

Devin is also crap

[@user-tx9zg5mz5p]

Humans need to unionize against ai and robots...

[@galailliz]

Third comment

[@allnewjient7651]

loser 3

[@galailliz]

Second comment

[@allnewjient7651]

loser 2

[@galailliz]

Fourth comment

[@ashtwenty12]

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

[@DJWESG1]

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.

[@gooodreason]

Crazy, big and pretty pretty shocking 🥱 Dude your reports work better than any sleeping pills 😂👍