Swarms of AI Agents STUN the Entire Industry | 100 Million Jobs GONE? | Devin, Maisa, Groq & more

Summary

The transcript discusses the emergence of AI software engineers like Devon and the impact of AI agents on various industries. It highlights the capabilities of these agents in performing complex tasks, such as setting up projects and interacting with customers, emphasizing the potential for AI to augment human work. The video also touches on the development of specialized chips like the LPU and KPU, designed to enhance AI inference speed and functionality. The speaker, Wes, shares his insights on the future of AI and its accessibility, encouraging viewers to share their thoughts on AI's role in their lives through a survey.

Takeaways

• 🤖 Devon, the first AI software engineer, is making headlines and raising discussions about the future of software engineering roles.
• 🚀 AI agents like Devon are being rolled out to the public, with some people already using them for the first time.
• 🎥 McKay Wrigley's video demonstrates the impressive capabilities of Devon, highlighting the era of AI agents beginning.
• 🛠️ Devon's interface provides a chat, shell access, an ID, and a browser, allowing it to perform complex tasks like setting up a project from a GitHub URL.
• 📈 The video showcases Devon's planning and execution steps, such as cloning a repository and installing dependencies.
• 🤔 Ethan Mik discusses the new modality of interaction with AI coders, emphasizing the continuous background execution and debugging of ideas.
• 📊 AI systems are not yet fully autonomous and error-free, but they represent a fascinating starting point for future development.
• 🏢 The potential of AI agents to handle tasks like setting up websites and marketing campaigns could significantly reduce the time and effort required by humans.
• 📞 AI agents can also manage customer interactions, such as making phone calls and handling sales inquiries, almost seamlessly.
• 🌐 The AI landscape is rapidly evolving, with new models and technologies like GPT 4.5, zGPT, and various AI chips being developed.
• 💡 The future of AI suggests a shift in necessary skills, with domain expertise becoming more valuable than traditional programming knowledge.

Q & A

What is Devon, and why is it making news?

Devon is the first AI software engineer developed by Cognition Labs. It is making news because it represents a significant advancement in AI, with the potential to either replace or augment human software engineers. Devon is being rolled out to the public and has begun to be used by people for the first time.

How does Devon interact with users and execute tasks?

Devon interacts with users through a chat interface and has access to a browser, a command-line interface (CLI), and can run tasks in the background. It can read and understand project documentation, clone repositories, install dependencies, and execute complex technical steps based on the tasks given by the user.

What is the significance of the pulsing blue dot in Devon's interface?

The pulsing blue dot in Devon's interface indicates what the AI is currently working on. It provides a visual cue to the user about the status of the tasks being executed, showing live activity and the progression of the work being done.

What is the role of the AI agent in the future of work, according to the video?

The AI agent is expected to revolutionize the future of work by taking on tasks that humans currently perform, especially those that are monotonous or time-consuming. AI agents like Devon could potentially reduce the need for human intervention in various tasks, allowing individuals to focus on more complex or creative aspects of their work.

How does the video describe the potential impact of AI agents on businesses?

The video suggests that AI agents could significantly reduce costs for businesses by automating customer service and other tasks that currently require human labor. For example, AI agents could handle customer inquiries and transactions at a fraction of the cost of human agents, leading to substantial savings.

What are some of the other AI agents mentioned in the script?

Besides Devon, the script mentions McKay and Wrigley, who are impressed by Devon's capabilities, and Ethan Mik, who discusses the new modality of interaction that AI agents like Devon offer. Additionally, AI Jason is mentioned, who provides insights into the potential of AI in various applications.

What is the significance of the language processing unit (LPU) mentioned in the script?

The language processing unit (LPU) is a specialized hardware accelerator designed to improve the inference speed of AI models, enabling real-time AI applications. LPUs, like GPUs (graphics processing units), are tailored for specific types of computations, in this case, language processing, which is crucial for AI agents to understand and generate human language effectively.

How does the video address concerns about AI replacing human jobs?

The video acknowledges that AI systems are not yet capable of performing tasks autonomously without errors and that there is still work to be done before they can be fully trusted with major projects. However, it also suggests that AI will lead to a shift in the types of skills that are in demand, with a focus on domain expertise rather than traditional programming skills.

What is the role of domain expertise in the context of AI?

Domain expertise becomes increasingly important in the context of AI because it allows individuals with specific knowledge in a particular field to utilize AI technology effectively. AI provides the computational power and intelligence to carry out tasks, but domain expertise guides the AI in the right direction and ensures that the outcomes are relevant and useful.

What is the potential future scenario where AI agents are widely accessible?

The potential future scenario outlined in the video is one where AI agents are accessible to everyone, allowing individuals to hire 'intelligence on demand' for various tasks. This could lead to a significant shift in how work is done, with AI agents taking care of monotonous or time-consuming tasks, freeing up humans to focus on more complex and creative endeavors.

What is the upskilling process mentioned by Jensen Huang, CEO of Nvidia?

The upskilling process mentioned by Jensen Huang refers to the need for individuals to learn new skills in the age of AI. As AI takes over tasks that were traditionally done by humans, the focus shifts to domain expertise and the ability to effectively use AI technology. This process is expected to be 'delightful' and 'surprising', as it will open up new possibilities for individuals across various fields.

Outlines

00:00

🤖 Introduction to Devon: The AI Software Engineer

The video begins with an introduction to Devon, the first AI software engineer that has been making headlines. It discusses the potential impact of AI agents like Devon on the future of software engineering, whether they will replace or augment human engineers. The video creator shares firsthand experience with Devon, demonstrating its capabilities in setting up a complex project from a GitHub URL. The AI's workspace is shown with access to chat, CLI, an ID, and a browser, highlighting its ability to execute tasks in real-time.

05:02

🚀 AI Agents Transforming Productivity

The video continues with a discussion on how AI agents are changing productivity and work dynamics. It features comments from McKay Wrigley, who is impressed by Devon's capabilities. The video creator shares his experience of using Devon to set up a project, highlighting the AI's ability to read a readme, clone a repository, identify a package manager, and install dependencies. The segment also touches on the potential of AI agents to handle multiple projects simultaneously, working around the clock, and the excitement around the new modality of interaction with AI.

10:03

🌐 Real-World Applications of AI Agents

This paragraph delves into real-world applications of AI agents, such as automating the setup of websites and handling customer inquiries. The video creator reflects on his experience in e-commerce and online business, discussing the time-consuming tasks that could potentially be automated by AI. It also explores the limitations of AI, such as the inability to conduct sales calls or handle customer objections without human intervention. The video introduces AI Jason, a YouTube channel discussing Gro, an AI that can generate text, transcribe voice, and handle real-time phone calls, showcasing the potential of AI in customer service and lead generation.

15:05

💡 The Future of AI and Business

The video discusses the future of AI in business, highlighting the potential cost savings for companies by replacing human customer service agents with AI. It mentions various AI models and platforms, such as GPT 4.5, zGPT, and Chatbot Arena, and their rankings based on user preferences. The video emphasizes the collective intelligence of global experts working on AI agents and infrastructure, and the potential for AI to democratize access to intelligence, making it more affordable and accessible.

20:05

📈 Empowering Individuals with AI

The final paragraph focuses on the empowerment of individuals through AI, suggesting a future where intelligence is no longer a luxury for the wealthy. It discusses the shift from human intelligence being expensive and scarce to AI making intelligence more accessible and affordable. The video creator shares a survey to gather community input on AI and expresses a desire to involve the community in future plans. The video ends with a call to upskill and adapt to the changing landscape brought about by AI, with a vision of a future where everyone can leverage AI to enhance their domain expertise.

Keywords

💡AI software engineer

The term 'AI software engineer' refers to artificial intelligence systems, like Devon, that are designed to perform tasks typically associated with software engineers. These tasks include coding, debugging, and project management. In the context of the video, Devon is an AI agent that can understand complex instructions, interact with a browser, and execute coding tasks, thereby augmenting or potentially replacing human software engineers in certain scenarios.

💡Cognition Labs

Cognition Labs is the company behind the development of Devon, the AI software engineer mentioned in the video. The company is at the forefront of creating AI agents that can assist or replace human workers in technical fields. Their work signifies a shift towards more automated and intelligent systems in software engineering and other domains.

💡AI agents

AI agents refer to autonomous systems or programs that can perform tasks, make decisions, and interact with humans or other systems in a way that resembles human intelligence. These agents are designed to augment human capabilities or automate processes, leading to increased efficiency and productivity.

💡Natural Language Processing (NLP)

Natural Language Processing is a subfield of artificial intelligence that focuses on the interaction between computers and humans through natural language. It involves enabling computers to understand, interpret, and generate human language in a way that is both meaningful and useful. NLP is a critical component in the functionality of AI agents, allowing them to communicate effectively with users.

💡Grok

Grok, in the context of the video, refers to a Language Processing Unit (LPU) developed by the company Grok. It is a specialized hardware designed to accelerate the inference capabilities of AI models, allowing for real-time text-to-speech and voice-to-text conversions. This technology is crucial for applications where AI agents need to interact with humans through natural conversations.

💡Customer service automation

Customer service automation involves the use of technology to handle customer interactions with a business, often through AI agents or chatbots. This can include answering frequently asked questions, processing orders, and resolving customer issues. The goal is to provide efficient, cost-effective, and scalable support while improving customer satisfaction.

💡Upskilling

Upskilling refers to the process of acquiring new skills or improving existing ones to enhance an individual's capabilities and employability. In the context of AI, upskilling involves learning how to work with AI technologies, leveraging them to improve productivity, and adapting to the changing job landscape as AI systems become more prevalent.

💡GPT-4.5

GPT-4.5 is a speculated version of OpenAI's Generative Pre-trained Transformer models, which are advanced AI language models capable of generating human-like text based on the input they receive. GPT-4.5 is expected to have improved capabilities over its predecessors, including better understanding and generation of text, which could lead to more sophisticated AI applications.

💡Multi-agent code generation

Multi-agent code generation refers to the process where multiple AI agents collaborate to produce code, often through an iterative process of testing and optimization. This approach can lead to more efficient and effective software development by leveraging the strengths of multiple AI systems working together.

💡Knowledge Processing Unit (KPU)

A Knowledge Processing Unit (KPU) is a type of hardware designed to optimize the processing of knowledge and information, particularly for AI applications. It is analogous to a Graphics Processing Unit (GPU) but specialized for AI tasks such as understanding and generating language, making it a critical component for AI agents that require fast and efficient data processing.

💡AI inference speed

AI inference speed refers to how quickly an AI system can process input data and generate an output or response. This is particularly important for real-time applications where rapid responses are necessary, such as in conversational AI or autonomous decision-making systems. Faster inference speeds allow AI systems to interact more seamlessly and naturally with humans.

Highlights

Devon, the first AI software engineer, is making news and raising discussions about its potential to replace or augment human software engineers.

Devon is being rolled out to the public, with some people already using it for the first time.

McKay Wrigley's video demonstrates the impressive capabilities of Devon, showcasing its real-time project setup from a GitHub URL.

Devon's interface includes chat, a shell for CLI commands, an ID for authentication, and a browser for web interactions.

The AI agent can plan and execute tasks autonomously, such as cloning a repository and installing dependencies.

Ethan Mik discusses the new modality of interaction with AI agents like Devon, emphasizing the continuous background execution and debugging of ideas.

AI agents could potentially revolutionize productivity and work processes, allowing for asynchronous task management and execution.

Despite the excitement, AI systems are not yet ready to work autonomously without human oversight or assistance.

The potential of AI agents to reduce the time and effort required for tasks like setting up online stores or marketing campaigns is significant.

AI Jason's YouTube channel discusses GPT and its applications, including a live demonstration of an AI agent making a phone call.

Grock's Language Processing Unit (LPU) aims to set the standard for Gen AI inference speed, enabling real-time AI applications.

MSA AI Mesa's Knowledge Processing Unit (KPU) is showcased in a demo helping a customer with an order issue, highlighting the potential cost savings for businesses.

The development of AI agents is attracting the brightest minds from various fields, indicating a shift in focus towards AI technology.

GPT 4.5 and other advanced models are on the horizon, with potential releases and updates expected soon.

Chatbot Arena's rankings show the preference for different AI models, with newcomers like Claude 3 Opus gaining popularity.

The future of AI suggests a shift towards domain expertise being more valuable than traditional coding skills.

Jensen Huang, CEO of Nvidia, envisions a future where everyone can be a programmer through natural language programming, thanks to AI advancements.

Upskilling in domain expertise and adapting to new AI technologies will be crucial for success in the evolving job market.

Community engagement and feedback are essential for shaping the future of AI applications and accessibility.

Transcripts

so at this point you probably heard

about Devon the first AI software

engineer this AI agent has been making

some news a lot of people have their own

takes on how far this will go to either

replace software Engineers or augment

them it's slowly being rolled out to the

public and we're beginning to see it

being used by some people for the first

time but here's the thing this one is

the first of many because on the heels

of Devon's announcement from cognition

Labs a number of other similar agents

are dropping buckle up so here's McKay

Wrigley he's saying I'm Blown Away by

Devon watch me use it for 27 minutes

it's insane the era of AI agents has

begun I'll link this below if you want

to see it but let me just highlight a

few portions of this video okay guys

we're going to just jump in right away

so I'm going to send this off to Devon

right now so yes we are in Devon we are

in cognitions New AI software engineer

basically what I'm doing is I'm in the

chat here and has access to a browser

here you can see following is on again

this indicator shows us live um just to

draw your attention to a few other

things here this pulsing blue dot with

this grade text is basically indicating

what Devon is up to right now is I'm in

the chat here and I'm asking Devon to

set up this project and what I did was I

gave it a GitHub URL which links to my

chatbot UI project and I basically want

to see can it set it up like this is the

read me for this project it's a fairly

complex setup which is is something I'd

expect a software engineer to be able to

do basically you can see over here is

our chat and then over here is Devon's

workspace okay and so if we go into quad

view here Devon has four things has

access to our chat has access to a shell

so it can run a CLI it has an ID which

will be right here once that begins if

it needs that step and it has access to

a browser here and this just follows it

live okay we can actually see like a

history of what it's done right here

which is pretty cool this pulsing blue

dot with this gr text is basically indic

what Devon is up to right now you know

we're just sitting here waiting for it

to complete tasks okay every once in a

while Devon will actually this will turn

orange and it will need information cre

look at a few things so you can see over

here Devon is in its planner so you can

see that Devon has a planning step here

here are all the steps I need to

accomplish based on the task I was given

right and it just came up with that list

by itself so step one was cloning the

repository from get a blink we gave it

it ran get clone with the URL

so it cloned that it finished and then

it marked it as done in the planner then

you can see this next step which it was

doing while I was just talking was

identify the package manager and

installed the dependencies so what it

actually did was it ran npm install here

basically that's just installing a bunch

of like prepackaged software and now

it's just doing its thing so you can see

we got a little message from Devon said

I've clone the repo I'm reading the read

me it's basically just constructing a

plan based on reading the readme and

sure enough like these are all the steps

I would expect a regular software

engineer to follow right CL on the repo

read the instructions install the

packages and then in this particular

project we have to set up a super Bas CI

so that's basically the back end

basically we we want it to basically get

to this step and just get to the app

Devon's now trying to install super base

which is pretty impressive this is a

fairly complex technical step so

basically using the command line here

Devon's now downloading more or less our

our database that we use for the app and

the reason I'm recording this and the

reason I'm so excited about this is

because this really feels like the chat

GPT moment for agent products so

definitely sounds like pretty good

feedback here's Ethan mik we've covered

him and a few of his posts before on

this channel so it seems like he's

working a lot at kind of the

intersection of working productivity and

AI that whole blog post about the jagged

Frontier and cyborgs and centaurs was

his work he was one of the people in

that study so looks like he's got a a

book coming out co-intelligence which I

would guess would be pretty good and

he's saying this the thing that makes

Devon the AI coder really interesting is

the new modality of interaction you can

talk to it at any time like you would a

person and it just keeps chugging away

in the background executing and

debugging your ideas and so here's just

kind of a time laps of the project that

he was doing and this is true with a lot

of previous ones even something like

Chad Dev and autogen where you can have

multiple ages kind of strung together

working together even autogen I mean you

can take turn speaking but it is kind of

a turn based approach with Chad Dev you

kind of give them the higher level task

and they get to work they talk back and

forth but this kind of interface is it

seems like it's the first view of what

the future of Agents will look like it's

not going to be a back and forth you

will kind of asynchronously whenever you

have time or ideas just kind of dump

them into the chat right the agents

might even have multiple projects

running potentially you kind of add

information as needed and the agent is

always working as long as it kind of has

some more subtasks to complete it keeps

going and and building them 24 hours a

day I mean this is a lot more like you

would with somebody that that works for

you for example you know if you hired

somebody to help you with a project you

give them the top of task they start

working you add feedback and any other

information they might know but they're

they're kind of working that whole time

he's saying to be clear AI systems

aren't quite there yet to do this work

autonomously and airror free without

help even afterward there's a waste to

go before you would want to trust a

major project to AI but it is a

fascinating start nevertheless he's

saying I can't code in Python it is

doing everything autonomously based on

my request for a website that explains

how dilution Works in startup funding I

can't help but feel excited I can't wait

to see this done so I've shared a little

bit of my background on this channel a

couple times but I've been kind of in

the e-commerce space online business ads

whatever you want to call it for the

last decade plus so I've built a lot of

websites and Shopify stores and a lot of

campaigns and and setup servers and

tracking and analytics and just

everything everything everything and

I've done it so many many many times to

where I mean it's it's it's fairly easy

for me now but still if you want to be

effective at something like this you

have to be able to get through a lot of

manually doing stuff right to set up an

online store you know you can see that

as 2 hours of your focused attention you

want to set up a marketing campaign with

landing pages you know that's 3 to 5

hours depending on the complexity you

know if upsells or whatever of your

focused undivided attention we're

getting closer to the time when a lot of

that is going to be done with a simple

sentence maybe over time you'll build

kind of a copy and paste little cheat

sheet of command prompts that of prompts

that that work really well to create the

right thing for you some sort of custom

instructions and then you just say it

and this thing goes and it builds it

builds stores blogs landing pages so

what though so what happens so if I set

up a gym website like I still have to

take the phone calls right when the

customers come in and I still have to

sell them on it right I have to convince

them to buy whatever product that I'm

selling that still work AI can't do that

work well let's see so this is AI Jason

AI Json uh is a YouTube channel and he

kind of comes out of nowhere every once

in a while and just drops some fire and

so I do want to highlight this one his

latest is talking about Gro he does a

deep dive into Gro with a Q so that's we

we've covered that a little bit I've did

a little bit more research into grock

since then and yeah it's the real deal

you're you're on uh Cloud n it

seems I don't know how people hate that

guy but in this one Jason basically goes

through talks about grock what is the

lpu the language processing unit how

it's different which that's what grock

is basically and then later he like live

just you know kind of uh on video builds

this app that uses grock and text to

voice and builds this little app and

take a look at what this app does so

this is like a Skype chat where he's um

you know he visits the website whatever

and then submits his information um you

know so this is like a chat app which we

know chat Bots can do chat apps okay but

what happens next next he receives a

call on his phone let's listen in my

and is start calling this function

called you can see it called a function

called cor pers our phone and if I

switch to my phone I actually do get a

phone call from the AI agent so I can

click accept to receive

it hi Jason I'm reaching out from crazy

Fitness regarding your interest in our

gym memberships I'm here to provide you

with all the information you need and

answer any questions you might have

thanks for calling no problem so what

specific fitness goals are you looking

to achieve uh I just want to lose some

weight I haven't do exercise at all for

the past three or six months since Co I

totally get that our personalized

training and nutrition programs can help

you reach your weight loss goals let's

discuss the membership options that are

best for

you okay sounds good I think I'm pretty

happy to just go ahead and get the

membership start this Saturday if

possible great to hear that to complete

the process I just need your credit card

number to secure your

membership

okay so my credit account number is

12341234 4231

4231 thanks Jason you're all set see you

on Saturday all right thanks byebye once

I finish the phone call it will actually

send the transcript back to the agent

session so you can see that it has

message just call the pur back below is

a transcript and based on this

transcript then the agent will be able

to decide next step after set up this

hook we will first add it then we will

something like this this and calling the

function called you can see it called a

function called call Press about phone

and if I switch to my phone I actually

do get a phone call from the AIA as you

can see here that entire thing has been

handled by the agent the the

conversation has been saved as a

transcript now you can you know extract

the credit card number out of that you

can probably automate that although you

know maybe initially just do it yourself

so it doesn't mess up but the point is I

mean that was a live call as far as you

can tell it was kind of going back and

forth pretty seamlessly he wasn't

waiting on the AI to respond and that is

new that hasn't really been around for

that long where that could happen that

quickly that fast so we're at a time

when this AI can generate text and near

instantly transcribed into voice and so

the input the like as you say things

that voice to text happens then the chat

bot the llm generates a response then

takes that response as text turns it

into voice and outputs of back and all

of that happens you know near instantly

or at least at conversational speeds

what is the thing that makes it possible

well that's Gro so instead of a GPU a

graphics Processing Unit you have an lpu

a language processing unit and so

they're saying grock is on a mission to

set the standard for Gen AI inference

speed so inference speed inference is

the response right so how quickly does

it generate its response helping

realtime AI applications come to life

today so are you picking up what I'm

putting down so you have something like

this building out your entire online

ecosystem marketing campaigns websites

capture forms whatever you have the

customers call in your phone number or

start a chat where the bot can talk to

them talk back and forth to try to get

them to either call in or just check out

when they call in a lovely cheerful and

excited voice pick up to answer all your

questions handle your objections and

collect your payment details now you

might be thinking yeah but so what that

still leaves the worst part you still

have to deal with those customers like

if those stupid customers mess up right

they I don't know they put the wrong

address somewhere or whatever like I

still have to troubleshoot and deal with

that don't I well let's see so here's

MSA AI Mesa Ai and so they're powered by

a kpu they have a paper on it I looked

through it briefly so there's a little

bit I think of of marketing speed going

on here cuz the kpu the knowledge

Processing Unit generally that's

deserved for you know that's kind of how

we name our chips right so this is

basically just a what would you call it

a software stack now some people are

kind of calling them out like saying

well unless we're missing something this

is an architecture based on well-known

patterns so like we we've seen this

before they're well put together they're

wrapped around an API and sold as a

service the point is don't read too much

into like the marketing thing but that

doesn't mean it's not good and again

this will keep happening and people will

keep pointing it out and and yes

Shenanigans can be annoying even the big

tech companies are seemingly now

engaging in various forms of shenanigans

to make their product appear better than

it is to Edge out the competition but at

the end of the day is it good does it

work so here's a demo of them helping a

customer for question about an order

that did not arrive this time the

customer accidentally did not write the

order ID correctly so basically this

thing the kpu as they're referring into

it I didn't dive too much deeper but it

just sounds like you know they took a

large l language model GPT 4 or whatever

and they just they they added some

things to it some some functionalities

some code and whether it was brand new

or not doesn't matter it just sounds

like they they executed whatever they

did pretty well and so now this thing is

working kind of like deavon but whereas

Davin is a little bit more for software

development and stuff like that this is

a little bit more multi-use so here the

agent basically starts by understanding

what's happening in the context of this

email they're reading this email that

they're ping from email. text and it

really spells out like hey we got to

really understand what this person wants

next they're loading the orders CSV to

see whether or not it's correct next

upep they open up the orders file to see

what orders are in there to try to find

the customer file and then try to

identify the specific order that the

customer is talking about and then they

find the order and they respond to the

customer telling them that it's marked

as being in transit in our system and

saying because we are so sorry let me

give you a coupon code for 20% discount

on your next purchase with us and so

this is just one small task that it can

do you know you can expand and check its

reasoning process to see if there's any

mistakes that are that have been made or

anything like that how much did it cost

to answer that customer email well 21

cents you know and 45 seconds if you

want it run without explanations or 96

seconds with explanations which I don't

know if that even matters I mean when

we're talking about answering customer

emails I mean it could take hours and

still be very much faster than the

expectation there's a weight list for

the Early Access and again so this is

just one example of what's coming some

people are dunking in the thing cuz they

you know of their how they name things

but regardless of what any one

particular app or agent or company that

creates them how well they do the point

is there's a lot of them and they're all

working to create an agent for every

business the sheer amount of money

somebody that can create an agent that

does customer service or any other

specific thing the amount of money that

can be made is massive because companies

are already spending massive amounts of

money on that so if they're able to cut

the cost you know 10% it's a no-brain

for them with a lot of stuff like this

they're cutting their cost 99 plus per.

if you go from paying human customer

service agents to something like this

again what was it 21 cents to answer an

email I mean that's massive and the

people building all this stuff they're

smart like really smart for example for

recognition Labs they're saying our team

is small and talent dense all founding

team has 10 II gold medals II is of

course the bad guys in Ready Player one

so it's it's either that which which

this would make them the bad guys or

possibly it's the international Olympiad

in informatics which is an annual

competitive programming competition

where the best and brightest from all

over the world compete in various

complicated tasks usually involving

writing a computer program so that that

probably makes more sense I would say

that this makesense some really really

smart and there are leaders and Builders

who have worked at The Cutting Edge of

Applied AI at companies like cursor

scale AI lunch Club modal Google deep

mine weo and neuro this was from January

of this year agent coder multi-agent

code generation with iterative testing

and optimization and we have you know

Hong Kong Shanghai London Sussex various

Global researchers working on this stuff

attempting various architectures to to

build these agent coders now you might

have heard the leaks about GPT 4.5 5

turbo so it seems like potentially

somehow there's an index paged in Google

with open AI you know setting that

announcement for releasing GPT 4.5 turbo

in June or at least they're saying that

it will have a knowledge cut off of June

which could maybe sounds like that's

when it's ready to be released by

potentially secondhand rumor Sam Alman

thinks GPT 4.5 will automate 100 million

jobs globally also UCI University of

California Irvine is launching zot GPT

what is z GPT well it's built on top of

open AI so it's using one of the GPT

models from open AI it provides no cost

access to various open AI models

basically for faculty and staff this is

the way back machine so this is kind of

a snapshot of how this web page looked

like when this was launched on the on

March 12th they did list the model as

GPT

4.5 when they published this blog right

in here they're kind of saying that the

a AI model is gpc4 but they have more

planned so so it sounds like they're you

know talking to open AI open saying hey

we have something coming and if you've

been following some of my videos I don't

remember if it was a few months back or

a month ago late at night one night a

lot of people found that including

myself cuz I ran the test I actually

recorded it but Chad GPT was convinced

that it was running on GPT 4.5 turbo but

whatever the case is the point is the

bigger better models are coming very

soon the next GPT the next Gemini even

if Google and openi cease to exist well

here's chatbot Arena the rankings for

all of the different LM models by at

this point 408,000 people that have

tested them blindly so they they don't

know which ones they're using and they

just vote based on how good the results

are so kind of this is a representation

of what models people prefer so GPT 4 is

on top but uhoh what's this we have a

newcomer that I mean I'm going to go

ahead and say this is number two right

cuz the first models GPT 4 right so this

is you know after GPT this is the next

best model tra trailing by just a few

points here that's not that big of a

difference all right and it's Claude 3

Opus that's the model that everybody was

freaking out cuz it was so self-aware

they one to describe itself as some sort

of a hyper intelligent octopus with

infinite tendrils lashing out in all

directions which you got to give it

credit for style what's crazy is that

CLA 3 Sonet the smaller model also Opus

is the the top this one's the next down

and then the ha coup I believe is the

next one but Opus beats out Bard Gemini

Pro that's connected to the internet

that's online and clae 3 Sonet beats out

the older versions of GPT 4 and also the

mistal models and this is important to

understand so we're seeing progress

across everything we're seeing progress

across chips and how fast they respond

we see progress across the agent

architecture kind of how we're building

them a long time ago the smartest people

in the world were working on various

physics projects nuclear energy Etc

somewhat more recently the smartest

people in the world were working on how

to get you to click on ads how to get

you engaged in various content online

and now all those smartest people and

there's a lot more of them now when they

can all talk to each other globally all

of them are working on this AI agents

chips anything in this infrastructure

where they can be useful this is what

they're building one things that a lot

of you in the comments have asked

repeatedly this is kind of a theme that

I see is like what do we do what do we

build how do we sort of you know what do

we do we don't want to sit on the

sidelines we want to go out there we

want to create stuff and I know a lot of

you are building stuff and it's very

impressive so I posted this very

recently just an hour ago as I'm

recording this and it's basically asking

people to answer a few questions for me

to understand what they're looking to do

with AI what they're struggling with so

many of you responded that it blew past

my free tier limmit at type form so I

just updated it so if you've tried to

get in and it said it's broken or

whatever try again we should have plenty

of room now so I'll post this link below

if you can take two minutes share some

of your thoughts with me I would greatly

appreciate it it's not a weird thing to

harvest some data from you your email or

anything like that I just literally just

want to know what you think because I'm

getting a lot of people reaching out to

me that are Engineers Builders various

teams they have some interesting ideas

about what they're building or what they

could build so if some of that's useful

for us as a community I'll bring them in

put them in front of you I'm not sure if

everybody noticed but we haven't had any

sponsorships on this channel that's not

cuz people aren't asking to sponsor this

Channel That's cuz I'm saying no and

that's largely because we have an

amazing community and I have a few ideas

of how to involve all of you in deciding

where we all go next and to all the

people that feel a little bit confused

that a little bit ious about taking

advantage of the stuff that's happening

but not quite sure which direction to go

I have some ideas this survey will help

me refine some of my thoughts and we'll

we're going to be announcing some really

cool things in the upcoming days or next

week perhaps so really fast just a few

quick quotes here's Andrew a talking

about intelligence the power to apply

skills and knowledge to make good

decisions we invest years of our lives

and trillions of dollars on education

all to develop our ability to make

better decisions human intelligence is

very expensive this is why only the

wealthiest Among Us can afford to hire

huge amounts of intelligence like that

specialist doctor to carefully examine

think about and advise you on a medical

condition or a tutor that can truly take

the time to understand your child and

gently coach them where they need help

but unlike human intelligence artificial

intelligence can be made cheap so a

opens up the potential for every

individual to hire intelligence

inexpensively so that you no longer have

to worry about that huge bill from going

to see a doctor for falling sick or for

getting an

education and you'll be able to hire an

army of smart well-intentioned

well-informed staff to help you think

things through now think about what we

were talking about earlier about you

know for example building an online St

or like some sort of a gym website where

people input their data their phone

numbers then the sales agent calls them

in the past you needed money you need

the capital to buy intelligence right

cuz intelligence was only really

available in humans and we're lazy and

cranky and we sleep 8 hours a day we're

expensive intelligence is expensive

because it's scarce what happens when it

gets cheaper or specifically what

happens where it's more accessible what

happens when you and I we can have

Intelligence on demand intelligence to

complete various tasks that either we

can't do or maybe you know we could do

but we don't have enough time or it's

too monotonous or whatever if we could

just spin up these agents and they would

go and take care of it for us how much

easier would life be would it be easier

to do research and run a business and

make sure all your bills are paid have

something that keeps track of your

calendar that used to be only available

to the wealthiest of people hiring

people hiring assistants was not

available to everybody and now

potentially in the future it would

become more and more accessible here's

Jensen hang so he is the CEO the founder

of Nvidia and here he's talking about

whether or not you will need to learn

how to program now we'll do a video on

this in a little bit because I kind of

want to dive deeper into this but notice

what he says will be important when we

don't need to program what will be the

skill that is needed if the text stuff

becomes infinitely easier it's it's

going to sound completely opposite of

what people feel over the course of the

last 10 years 15 years um almost

everybody who sits on the stage like

this would tell you it is vital that

your children learn computer science um

everybody should learn how to program

and in fact it's almost exactly the

opposite it is our job to create

Computing technology such that nobody

has to program and that the programming

language is human everybody in the world

is now a programmer this is the miracle

of artificial intelligence the countries

the people that understand and how to

solve a domain problem in digital

biology or in education of young people

or in manufacturing or in farming those

people who understand domain expertise

now can utilize technology that is

readily available to you you now have a

computer that will do what you tell it

to do it is vital that we upskill

everyone and the upskilling process I I

believe will be delightful surprising so

it's that idea of domain expertise you

need to be good at whatever it is that

you chose to be good at ni AI provides

all the other things that you might need

it provides the intelligence to carry

out those tasks provides the tech

abilities to build some of the tech that

you need so as he says coding is just

done in natural language but I think the

really big Point here is that we all

need to upskill and potentially not in

the same skills that we're used to I

will on this channel do my best to try

to provide whatever help I can again

fill out that survey down below so I

know what you need and thank you for for

being part of this community I seriously

mean that my goal is to hopefully get to

know a lot of you better we have some

big things planned I'll leave it on that

my name is Wes rth and thank you for

watching