ChatGPT Can Now Talk Like a Human [Latest Updates]

ColdFusion
20 May 202422:20

Summary

TLDRThe video discusses the latest advancements in AI with a focus on Open AI's new chat GPT 40, a model that integrates audio, vision, and text in real-time. It explores the potential of this technology as a digital assistant, its applications in various fields like education and robotics, and the ethical considerations it raises. The video also touches on Google's response with its AI models and the implications of these developments for the future of technology and society.

Takeaways

  • 💡 OpenAI's new demo showcases the capabilities of ChatGPT 4.0, which can reason across audio, vision, and text in real time.
  • 🎬 The demo's realistic voice interactions remind the speaker of the movie 'Her,' with expressive and empathetic voice responses.
  • 📊 ChatGPT 4.0 can analyze and describe plots, providing insights into data such as temperature trends with notable events.
  • 🗣️ OpenAI announced a free version of ChatGPT 4.0, featuring an AI-powered search engine to compete with Google, multimodal capabilities, and improved text-to-speech models.
  • 🔍 ChatGPT 4.0 Omni is designed to naturally interact with humans, offering quick, efficient responses and larger context windows for complex tasks.
  • 🤖 AI is evolving to perform various tasks, such as tutoring students, assisting visually impaired users, and supporting customer interactions with advanced reasoning and multimodal capabilities.
  • 💼 Recent AI hardware launches, such as Rabbit R1 and Humane AR, have faced challenges, but software advancements like ChatGPT 4.0 Omni are reshaping the AI landscape.
  • 🎓 AI's potential in education raises questions about its impact on learning and critical thinking, as it could become a versatile, on-demand tutor.
  • ❤️ The emotional aspect of AI interactions is growing, with concerns about reducing face-to-face interactions and increasing social anxiety among younger generations.
  • 📱 Competition in the AI space is intensifying, with Google announcing new AI models and integrations, and rumors of an OpenAI and Apple partnership potentially transforming the tech landscape.

Q & A

  • What is the video about?

    -The video discusses the advancements in AI, particularly focusing on Open AI's new chat GPT 40 model, its capabilities, and implications for the future of AI and technology.

  • What is the significance of the new chat GPT 40 model by Open AI?

    -The chat GPT 40 model is significant because it can reason across audio, vision, and text in real time, offering a more humanlike interaction and quicker response times compared to previous models.

  • How does the new chat GPT 40 model differ from previous voice-based applications?

    -The new chat GPT 40 model is more humanlike with a quicker response time and the ability to handle longer, more complex tasks without losing context, making it more realistic and efficient than previous voice-based applications.

  • What is Open AI's strategy with the release of the new model?

    -Open AI has released a free version of the application, an AI-powered search engine to compete with Google, and introduced multimodal capabilities and improvements through a new text-to-speech model.

  • How does the video compare the new chat GPT 40 model to digital assistants like Siri?

    -The video suggests that the new chat GPT 40 model is a significant improvement over digital assistants like Siri, which the speaker believes have been a wasted opportunity and do not provide a satisfactory user experience.

  • What potential use cases for the chat GPT 40 model are discussed in the video?

    -The video discusses potential use cases such as becoming a robust all-in-one assistant, helping visually impaired people through apps like be my eyes, and improving educational experiences for students.

  • How does the video address concerns about the accuracy of AI-generated content?

    -The video acknowledges the issue of 'hallucinations' in AI, where incorrect or misleading information is provided, and emphasizes the importance of ensuring the AI's responses are accurate, especially in educational contexts.

  • What is the potential impact of AI on the future of education as discussed in the video?

    -The video suggests that AI could revolutionize education by providing personalized, on-demand tutoring and support. However, it also raises questions about the potential overreliance on AI and its impact on critical thinking and learning.

  • How does the video explore the emotional aspect of AI interactions?

    -The video discusses the possibility of forming emotional bonds with AI, referencing the movie 'Her' and the rise of romantic AI partners, and questions the implications this could have on human interaction and mental health.

  • What are some of the challenges and ethical considerations mentioned in the video?

    -The video touches on challenges such as ensuring the accuracy of AI-generated content, the potential impact on critical thinking and social interaction, and ethical considerations regarding the training of AI models and copyright infringement.

  • What is the role of brilliant.org in the context of this video?

    -Brilliant.org is mentioned as a platform for learning about AI and related topics through interactive lessons, offering a hands-on approach to understanding concepts like large language models.

Outlines

00:00

🤖 Introduction to OpenAI's GPT-4 Omni and Interview Preparation

The video begins with an introduction sponsored by brilliant.org and leads into an exciting announcement about an upcoming interview with OpenAI. The host expresses enthusiasm for OpenAI's latest demo of their GPT-4 Omni model, which showcases capabilities in audio, vision, and text processing in real-time. The model's human-like interactions and quick response times are likened to the movie 'Her,' suggesting a significant leap in AI's ability to mimic human behavior. The host also discusses OpenAI's recent announcements, including a free version of their application, an AI-powered search engine to rival Google, and improvements in multimodal capabilities and text-to-speech models. The video sets the stage for an exploration of GPT-4 Omni's capabilities, use cases, and implications for the AI market and future.

05:02

🎲 GPT-4 Omni's Multimodal Capabilities and Real-world Applications

This paragraph delves into GPT-4 Omni's advanced features, such as its ability to interact naturally with humans, respond to audio inputs with minimal latency, and handle complex tasks without losing context. The integration of vision and speech allows the model to mimic a personality, positioning it as a potential digital assistant. The host engages in a playful interaction with the AI, demonstrating its personality and responsiveness. The video also touches on the AI's efficiency, cost-effectiveness, and the potential impact on the market for AI hardware devices. Furthermore, it explores the use of GPT-4 Omni in assistive technologies, such as helping visually impaired individuals with everyday tasks and the potential for humanoid robots in commercial applications.

10:04

📚 Exploring GPT-4 Omni's Educational Potential and Challenges

The host discusses the potential of GPT-4 Omni as an educational tool, demonstrating its ability to assist with math problems and coding issues. The video presents a scenario where the AI helps a student understand a math problem, emphasizing the importance of accurate information and the potential risks of AI 'hallucinations'—incorrect or misleading answers. The discussion also raises broader questions about the future of education with AI, including the impact on critical thinking and the possibility of AI becoming a common learning tool. Additionally, the emotional component of AI interaction is considered, with the potential for forming emotional bonds and the implications for face-to-face interaction and mental health.

15:05

💬 The Future of AI in Personal Relationships and Society

This section contemplates the future implications of AI on personal relationships and society. It raises the possibility of AI companionship and the emotional bonds that might form between humans and AI, as well as the societal reflections seen in the rise of romantic AI partners. The video also addresses concerns about how AI models are trained, touching on issues of copyright infringement and the underlying mathematics of modern AI. The host encourages viewers to learn more about AI through interactive lessons on brilliant.org, highlighting the effectiveness of learning by doing.

20:07

🌐 Competitive Landscape and OpenAI's Future Prospects

The final paragraph wraps up the video by discussing the competitive landscape in the AI industry. It mentions Google's response to OpenAI's advancements, including new projects and AI models that aim to integrate AI more deeply into daily products. The video also speculates on potential partnerships between Apple and OpenAI, suggesting that this could significantly alter the tech landscape. However, it also notes some behind-the-scenes drama at OpenAI, with key personnel leaving the company, which could impact its future. The host reflects on the rapid progress in AI and invites viewers to subscribe for more content on science, technology, and business.

Mindmap

Keywords

💡Open AI

Open AI is a research laboratory that focuses on artificial intelligence. In the video, it is mentioned as the company behind the latest advancements in AI technology, specifically the chat GPT 40 model. The script discusses the potential impact of Open AI's developments on the future of digital assistance and AI market.

💡Chat GPT 40

Chat GPT 40 is a flagship model developed by Open AI that is capable of reasoning across audio, vision, and text in real time. The video highlights its humanlike interaction and quick response time, suggesting it could revolutionize how we interact with technology.

💡Multimodal capabilities

Multimodal capabilities refer to the ability of a system to process and understand multiple types of input data, such as text, voice, and visuals. The video script mentions that Open AI's new model supports multimodal capabilities, which is a significant step towards creating more realistic and interactive AI experiences.

💡Text-to-speech model

A text-to-speech model is a technology that converts written text into spoken words. The video script discusses how Open AI has improved its text-to-speech model, which contributes to the more humanlike and expressive voice interactions in their AI applications.

💡AI-powered search engine

An AI-powered search engine is a search platform that uses artificial intelligence to enhance search results and user experience. The video mentions that Open AI has announced a free version of their application, which includes an AI-powered search engine to compete with Google.

💡Humanoid robot

A humanoid robot is a robot designed to resemble the human body in appearance and movement. The video script discusses the potential of AI software from Open AI to power humanoid robots, suggesting a pathway for more realistic and commercially viable robots in the future.

💡AI hallucinations

AI hallucinations refer to instances where an AI provides incorrect or misleading information, essentially making things up. The video script raises concerns about the potential for AI to provide inaccurate information, especially in educational contexts.

💡Be My Eyes

Be My Eyes is an app that connects blind or visually impaired people with sighted volunteers for assistance with everyday tasks. The video script mentions a collaboration between Be My Eyes and Open AI to improve the app's capabilities for the visually impaired.

💡AI tutoring

AI tutoring involves using artificial intelligence to assist students with their learning. The video script discusses the potential of AI, like Open AI's chat GPT 40, to act as a tutor, helping students understand concepts and solve problems, which could revolutionize education.

💡AI companionship

AI companionship refers to the use of AI for social interaction and companionship, often seen in chatbots and virtual assistants. The video script speculates on the future where AI might be used for companionship, reflecting on societal trends and the emotional aspects of AI interactions.

💡AI hardware devices

AI hardware devices are physical gadgets that incorporate AI technology for various functions. The video script mentions devices like the R1 and Humane pin, discussing the potential redundancy of such devices in light of advancements in AI software that can be integrated into existing platforms like smartphones.

Highlights

Interview with OpenAI for a software engineering role.

Latest demo from OpenAI showcasing the new chat GPT 40 model with multimodal capabilities.

Chat GPT 40's ability to reason across audio, vision, and text in real time, reminiscent of the movie 'Her'.

Faster response times and more humanlike interactions in the new demo compared to the previous version.

OpenAI's announcement of a free version of the application and an AI-powered search engine to compete with Google.

gp4 Omni's potential to revolutionize how we interact with technology after disappointing launches of other AI devices.

gp4 Omni's capability for natural interaction with humans, making it stand out from other AI models.

The use of gp4 Omni in AI robotics, such as in the company Be My Eyes, assisting visually impaired individuals.

OpenAI's focus on improving products for users with disabilities, showcasing a commitment to inclusivity.

The potential of AI to become a robust all-in-one assistant, as discussed in the video.

Concerns about AI 'hallucinations' providing incorrect or misleading information, especially in educational contexts.

The rise of AI in personal companionship and the potential societal implications of romantic AI partners.

Google's counter-announcements at their IO event, positioning them as a strong competitor in the AI space.

The departure of Ilya Sutskever, OpenAI's Chief Scientist, signaling potential internal changes within the company.

Speculations about a partnership between Apple and OpenAI, suggesting a shift in the tech landscape.

The rapid progress in AI capabilities over the past few years, moving from text roleplay to real-time voice interaction.

The ethical and practical questions raised by the increasing reliance on AI in various aspects of life.

Transcripts

00:01

this video was brought to you by

00:02

brilliant.org listen I got some huge

00:05

news oh do tell I'm all yours well in a

00:09

few minutes I'm going to be interviewing

00:11

at open AI have you heard of them open

00:14

AI huh sounds Vaguely

00:17

Familiar kidding of course that's

00:19

incredible Rocky what kind of interview

00:22

well it's for a software engineering

00:23

role but I just need to know that was

00:25

the latest demo from open AI showcasing

00:28

the brand new chat GPT 40 their Flagship

00:31

model that can now reason across audio

00:33

vision and text in real time of course

00:36

I'm probably not the only one but as

00:38

soon as I saw it it reminded me of the

00:40

movie Her the Expressions the emotions

00:43

and the empathetic nature of the voice

00:46

it's definitely one of the most

00:47

realistic voice-based applications that

00:49

I've ever seen I've used the old chat

00:51

GPT voice a fair bit and it's pretty

00:53

amazing but this demo was much more

00:56

humanlike with a much quicker response

00:58

time the feeling that these new

01:00

interactions conjure up is approaching

01:01

that of just talking to another regular

01:03

human on the phone if you're a longtime

01:05

viewer you know that I think that

01:07

digital assistance like Siri absolutely

01:09

suck and are a wasted opportunity but

01:11

I've talked about the next big step

01:13

being voice and for chat GPT in

01:15

particular to become a robust all-in-one

01:19

assistant well it seems like the time

01:21

has finally come with these latest

01:23

announcements open AI has announced a

01:25

free version of the application an AI

01:28

powered search engine to compete with

01:29

Google which will allow for

01:30

purpose-built assistance multimodal

01:33

capabilities and overall improvements

01:35

through a new textto speech model OKAY

01:38

chat PT I'm sharing with you the plot

01:40

now I'm wondering if you can give me a

01:41

really brief one- sentence overview of

01:43

what you

01:44

see the plot displays smoothed average

01:48

minimum and maximum temperatures

01:50

throughout 2018 with a notable

01:53

annotation marking a big rainfall event

01:55

in late

01:56

September fantastic I have another

01:58

question for you um which months do you

02:00

see the hottest temperatures and roughly

02:02

what temperatures do those correspond

02:04

to the hottest temperatures occur around

02:07

July and August the maximum temperature

02:11

during these months is roughly between

02:13

25° and 30° however we're going to be

02:16

focusing mostly on gp4 Omni because I

02:19

believe that this is the very start of a

02:21

massive change with how we're going to

02:23

interact with

02:24

technology after the disappointing

02:26

launch of the rabbit R1 and the disaster

02:28

that was the Humane AR I pin the strange

02:31

dichotomy of AI being both amazing and

02:33

terrible at the same time continues what

02:36

a time to be alive so in this quick

02:38

episode we'll take a look at gp4 omni's

02:41

capabilities the use cases for it and

02:43

what this all means for the AI market

02:45

and the future it's going to be an

02:47

interesting one so let's get into

02:49

[Music]

02:50

it you are watching to Fusion

02:54

[Music]

02:58

TV gp4 o where the O stands for Omni is

03:03

significantly different from everything

03:04

else I've seen so far the primary reason

03:06

is its capability to naturally interact

03:08

with humans well

03:11

Rocky you definitely have the I've been

03:14

coding all night look down which could

03:16

actually work in your favor maybe just

03:19

run a hand through your hair or lean

03:22

into the Mad Che slime Your Enthusiasm

03:25

is what's really going to shine through

03:26

I don't have a lot of time so I'm just

03:28

going to throw this on what do you

03:33

think oh Rocky that's quite a statement

03:37

piece I I mean you you'll definitely

03:39

stand out though maybe not in the way

03:42

you're hoping for an interview okay I

03:44

got it I got it hey Chad are you there

03:47

hey yeah I'm here what's up hey Let's do

03:51

let's have some fun uh I'd like you to

03:53

be super sarcastic everything you say

03:55

from now on is just going to be dripping

03:56

in sarcasm how does that

03:58

sound I ooh that sounds just amazing

04:03

being sarcastic all the time isn't

04:05

exhausting or anything I'm so excited

04:09

for this no the sasm let's get this

04:12

party started or whatever details like

04:16

it's laugh the quirky remarks and the

04:18

speech Cadence all makes this something

04:20

we've never quite seen before root root

04:24

for the

04:26

home no what was that

04:31

sorry guys I got

04:35

away chared what can I say sometimes I

04:38

just can't help

04:39

myself ready for another round according

04:42

to open AI it can respond to audio

04:44

inputs with as little latency is 232

04:46

milliseconds with an average latency of

04:49

320 milliseconds and that's similar to a

04:51

human response time during

04:53

conversation because it supports larger

04:55

context Windows it can handle longer

04:57

more complex tasks without getting

04:59

confused and losing the context of the

05:01

original request pair it up with vision

05:04

and speech integration and allow it to

05:05

mimic a personality and you're looking

05:07

at a real digital assistant uh we're

05:11

trying to figure out what should we play

05:13

do you have any

05:14

suggestions absolutely how about a

05:17

classic game of rock paper scissors it's

05:19

quick fun and you don't need great can

05:22

you count us in and sound like a sports

05:25

caster and welcome ladies and gentlemen

05:29

to the Ultimate Showdown of the century

05:31

in this corner we have the dynamic duo

05:34

Alex and Miana ready to throw down in

05:37

okay just count us

05:39

in all right here we go in 3 2 1 shoot

05:46

now show your hands what did you pick

05:48

who

05:49

won would you look at that it's a tie

05:54

okay let's do it again you can choose

05:56

from a wide range of voices to represent

05:58

the assistant but it's not all just

06:00

Aesthetics benchmarks indicate improved

06:02

reasoning across multiple

06:04

categories it's also more efficient and

06:07

cheaper as companies like Humane and

06:09

rabbit launched their AI Hardware this

06:11

year one of the most common questions

06:13

posed was Why Can't This just be an

06:15

application on a phone I've mentioned in

06:17

one of my episodes the new segment of AI

06:19

Hardware devices might be over even

06:22

before they start let's roll the clip in

06:25

time Google assistant or Siri could

06:27

simply be updated with similar capabil

06:29

ities to the R1 so the unfortunate truth

06:32

could be that this new segment might be

06:34

over as soon as it started I feel that

06:37

the latest update from open AI does

06:40

exactly that it may have just killed

06:41

handheld AI devices and to be fair the

06:44

recent updates and announcements from

06:46

Google and meta are proving that other

06:48

companies are in Hot Pursuit but the use

06:50

cases go well beyond that a few weeks

06:52

ago I did a video in figure an AI

06:54

robotics company that uses open AI

06:56

software to power its humanoid robot can

06:59

you explain why you did what you just

07:01

did while you pick up this trash on it

07:04

so I gave you the Apple because it's the

07:06

only uh edible item I could provide you

07:09

with from the table the demos were

07:11

impressive enough for certain tasks but

07:13

combining this with the latest updates

07:14

from open AI it becomes clear that

07:16

there's a pathway for more realistic

07:18

humanoid robots used for large scale

07:20

commercial

07:24

purposes one of the best use cases for

07:26

such technology is for those with a

07:28

visual disability

07:30

Mike Buckley is the chairman and chief

07:31

executive of be my eyes an app that

07:34

helps blind or visually impaired people

07:36

connect with users for everyday tasks in

07:38

late 2023 he talked about their

07:40

collaboration with open AI quote people

07:43

who were blind or have low vision were

07:45

directly involved in the development and

07:47

honing and Improvement of the product

07:48

when a lot of other companies would have

07:50

ignored it open AI put it on the front

07:52

burner and quote as part of the latest

07:55

announcements open Ai and be my eyes

07:58

showed how the app could be used for the

07:59

blind officially impaired is the king in

08:02

Residence at the moment yes it looks

08:06

like the king is in Residence right now

08:08

the Royal Standard flag is flying above

08:10

Buckingham Palace which is the signal

08:13

that the Monarch is present how exciting

08:15

to be there while the king is home but

08:18

that's not all it can

08:20

sing We Are chat gbt and O Chad gbt is a

08:25

base with a deep low booming voice and O

08:29

is a French soprano with a high-pitched

08:31

excited voice okay so what I want you

08:34

guys to do today is it's Friday May 10th

08:37

and we're in San Francisco I want you to

08:39

sing me a song about this I want you to

08:40

layer over each other and and I'm going

08:42

to continue to give you instructions as

08:44

you sing okay San Francisco in the month

08:48

of San Francisco in the month of May

08:52

it's a

08:54

Friday we are harmonizing we are

08:58

Harmon great thank thank you act as a

09:00

translator in real time um hey how's it

09:03

been going have you been up to anything

09:05

interesting

09:19

recently hey I've been good just a bit

09:22

busy here preparing for an event next

09:24

week recognize text and form appropriate

09:26

responses

09:29

okay I see it h no I didn't show you yet

09:33

just give me help along the way one

09:36

second whoops I got too excited I'm

09:40

ready when you

09:41

are so chat PT what equation did I write

09:46

down there ah I see it now you wrote

09:51

down 3x + 1 equals 4 yep exactly so

09:55

what's the first step I should take to

09:57

try to solve this the first step is to

10:00

get all the terms with X on one side and

10:03

no I have a lot of unknown values in my

10:05

life I'm totally convinced we I'm going

10:08

to learn math

10:10

now I love that attitude math can

10:14

definitely help solve some of life's

10:16

mysteries whenever you're ready to dive

10:18

into more math I'm here for you anything

10:20

else you'd like to tackle Today show it

10:22

to me whenever you're ready okay so this

10:24

is what I wrote down what do you

10:27

see a I see

10:29

I love chat chpt that's so sweet of you

10:34

hey chat

10:35

CHT hey there how's it going yeah it's

10:38

going really well I was wondering if you

10:39

could help me with uh a coding problem

10:41

today of course I'd love to help you out

10:45

what's the coding problem you're dealing

10:46

with okay I'm going to share with you

10:48

some code one second sure thing take

10:51

your

10:54

time okay so I just shared some code

10:56

with you could you give me a really

10:58

brief one- sentence description of

10:59

what's going on in the code this code

11:01

fetches daily weather data for a

11:03

specific location and time period

11:06

Smooths the temperature data using a

11:08

rolling average annotates a significant

11:10

weather event on the resulting plot and

11:13

then displays the plot with the average

11:15

minimum and maximum temperatures over

11:17

the year it can also take meeting notes

11:19

synthesize 3D objects create a photo

11:22

caricature and more and you might be

11:24

thinking didn't this all already exist

11:27

well yes a large part of it did

11:29

but without the speed accuracy or in the

11:32

case of an assistant the humanlike

11:34

interaction which in my opinion adds a

11:36

whole new dimension to it all devices

11:38

like the R1 and Humane pin would

11:40

recognize objects and talk back to you

11:42

but they' often get it wrong or fail

11:43

completely I'm still bitter about how

11:45

those launches went by the way but in

11:47

saying this attempts at a human level

11:49

assistant stretches even further back if

11:51

you can cast your minds back to Google

11:53

duplex which I covered 6 years ago in an

11:55

episode they integrated the technology

11:57

into Google assistant so it can make a

11:59

phone call on user's

12:04

behalf don't have something El you hi

12:08

I'm calling the book a women's haircut

12:09

for a client um I'm looking for

12:11

something on May

12:12

3rd sure I give me one nothing

12:20

mhm at the time it was very impressive

12:23

but Google did what Google does and

12:25

largely left the concept on the table

12:28

whether they were just too early or it

12:29

was a missed opportunity is a separate

12:31

conversation but compared to open ai's

12:33

announcement you can already see a major

12:35

difference in the way the conversation

12:37

takes place another fascinating use case

12:39

is seeing a student get help in real

12:41

time with their school work to try out

12:43

some of their new technology and so

12:44

we're curious about how good it might be

12:46

at tutoring someone in math on Khan

12:49

Academy so let's get it

12:52

started it's loading

12:54

up all right make sure I can see our

12:57

screen actually

13:00

in in this form hello there I'm here

13:03

with my son and I'd love you to tutor

13:05

him on this math problem but don't give

13:08

him the answer you can ask questions and

13:10

nudge him in the right direction but I

13:11

really want to make sure he understands

13:13

it himself and he's here in the room so

13:15

you can talk to him

13:17

directly of course I'd be happy to help

13:21

let's look at the problem

13:23

together can you first

13:25

identify which sides of the triangle are

13:28

the opposite adjacent and hypotenuse

13:32

relative to angle Alpha all right so I'm

13:36

pretty sure this is the angle Alpha

13:38

Right Here

13:39

Right cars correct now looking at the

13:43

triangle which side do you think is the

13:46

hypotenuse

13:48

um remember the hypoten I'm not totally

13:51

sure I think I think it might be this

13:54

one but I really am not sure this side

13:57

AC you're CL actually side AC is called

14:02

the adjacent side to the angle Alpha the

14:05

hypotenuse is the longest side of a

14:07

right triangle and is directly opposite

14:10

seeing a young student get help in this

14:11

way could end up being revolutionary but

14:14

before that can be the case we

14:15

definitely have to fix these

14:17

hallucinations if the AI is telling the

14:19

kid something wrong that could do more

14:20

harm than good hallucinations are

14:23

basically answers from an AI which are

14:24

incorrect or simply misleading basically

14:27

it makes things up despite improvements

14:29

that's not going to go away anytime soon

14:32

but speaking of education and the young

14:34

this opens up a broader

14:40

conversation while it's a great case

14:42

study for AI to help young students

14:44

learn if AI improves at the same rate

14:47

that it has been over the past 3 years

14:49

before we know it education would look

14:51

pretty different we then have to ask

14:53

ourselves some questions would an

14:54

overreliance on AI impact one's critical

14:57

thinking if students can generate essays

15:00

or generate the answers to math homework

15:02

how will the students learn themselves

15:04

but thinking outside the box what if

15:07

this is an outdated View and we just

15:09

don't see it yet what if in 5 years

15:12

educational AI systems arejust another

15:15

common learning tool imagine a free AI

15:17

package that also happens to be the

15:19

world's best tutor it could be flexible

15:21

to any students needs forever attentive

15:24

on demand 24/7 and can explain Concepts

15:27

in the specific way that individual

15:29

student can understand if in the future

15:32

students will benefit from AI or will be

15:35

held back by it still remains to be seen

15:37

but there's another problem even before

15:39

we can start thinking about such future

15:41

scenarios right now if unsupervised by

15:44

someone who doesn't know the knowledge

15:46

how do we know what the AI is spitting

15:47

out is even correct in the first place

15:50

for University level education for

15:52

example what if it's hallucinating

15:54

answers left and right but that's not

15:56

all there might be a strange emotional

15:59

component that we haven't really seen in

16:00

technology before consider future

16:02

Generations they'll grow up in a world

16:04

where a pretty accurate approximation of

16:06

human interaction is just a click away

16:09

it's going to mimic cleverness empathy

16:12

and even personality for those in gen

16:14

Alpha and Below would an emotional bond

16:16

form and will this subsequently reduce

16:19

face-to-face interaction even further

16:21

adding to social anxiety and other

16:23

mental health issues nobody knows but

16:26

these are questions worth thinking about

16:28

for adults this will be taken a step

16:30

further as we all know how good mate

16:32

Theodore in the movie Her fell head over

16:34

heels with his artificial intelligence

16:36

chatbot it's not going to be long before

16:38

a large number of people will look at

16:40

personal AIS for companionship we're

16:42

already seeing the rise in romantic AI

16:44

Partners even in such a primitive State

16:47

recently the founder of the dating app

16:49

Bumble said that the future of dating

16:51

could be one AI talking to another when

16:53

it comes to romance and AI it's not the

16:55

technology that's the problem it's more

16:57

of a reflection of our society

16:59

for more on that see my loneliness

17:01

epidemic episode Another concern has

17:04

always been how the companies are

17:05

actually training these models the

17:07

discussion on copyright infringement and

17:09

AI has been done to death so I'm not

17:10

going to spend too much time on it in

17:12

this episode but it's crazy to think

17:14

that all we've been talking about

17:16

falling in love with machines a machine

17:18

being a perfect tutor an aid for the

17:20

Blind and much more is all just matrix

17:23

multiplication in maths that's all that

17:25

modern AI really is but have you ever

17:27

wondered how it really works well

17:29

fortunately there's a fun and easy way

17:30

to learn about it with brilliant.org

17:32

brilliant is where you learn by doing

17:35

with thousands of interactive lessons

17:36

and maths data analysis programming and

17:39

of course AI their course on how large

17:42

language models work is especially

17:43

relevant for today's topic each lesson

17:45

on brilliant allows you to play with

17:47

Concepts a method proven to be six times

17:49

more effective than watching lecture

17:51

videos all content on brilliant is

17:53

crafted by researchers teachers and

17:55

professionals from MIT Caltech Duke

17:58

Microsoft Google and more learn at your

18:01

own pace whether it's for professional

18:03

development or your own self-development

18:05

to try brilliant for free for a full 30

18:07

days visit brilliant.org coldfusion or

18:11

click the link in the description you'll

18:12

also get 20% off an annual premium

18:15

subscription okay so back to the

18:18

[Music]

18:21

video as we wrapping up this video

18:24

Google came hitting back announcing a

18:25

ton of new things at their IO event

18:27

which is their annual Developers

18:29

conference these announcements will

18:31

truly keep open AI on their feet for

18:33

example project Astra which is Google's

18:35

answer to GPT 4 was announced this code

18:39

defines encryption and decryption

18:41

functions it seems to use aebc

18:45

encryptions also there were two new

18:47

Gemini AI models both are multimodal

18:50

more conversational and have improved

18:52

cross app compatibility vo which is

18:55

clearly Google's competitor to open AI

18:57

Sora will be a very interesting point to

18:59

watch in this AI race but perhaps more

19:01

importantly Google showcased how they're

19:03

intending to use AI across day-to-day

19:05

products like Drive Gmail meet and more

19:09

integrating AI natively into Google site

19:12

products could potentially solidify

19:13

market share in new news asking Gemini

19:16

to sum up my unread emails was an

19:17

intriguing Peak into a truly useful form

19:20

of AI assistance but on the other hand

19:23

what if Google's AI capabilities end up

19:25

being disappointing that could do just

19:27

the opposite and here the phone started

19:30

to slip it identified Michael Josh's

19:33

camera well enough but failed to

19:35

identify his heres battery pack and when

19:39

I asked it about that Starbucks coffee I

19:40

got it seemed to think the logo was a

19:42

person regardless I feel this is one of

19:45

the reasons why open AI made GPT 40 free

19:48

to users in order to onboard more

19:51

customers and to make things even more

19:53

interesting there have been Whispers

19:55

that apple is doing a partnership with

19:57

open Ai and when app comes out with what

19:59

they're planning this could

20:00

fundamentally change the current Tech

20:02

landscape imagine a native almost

20:04

perfect human-like assistant custom

20:06

built for iPhone perhaps and we'll just

20:09

have to see but back to open AI there's

20:12

actually been some drama behind the

20:13

scenes Keen observers noted how Ilia

20:16

satova open ai's Chief scientist and the

20:18

genius behind a lot of their success was

20:20

not part of any of the latest

20:22

announcements and this was strange and

20:24

suspicious because on most occasions he

20:26

would represent the company publicly

20:28

well well in just about a day after open

20:30

ai's latest announcements Ilia announced

20:33

that he was parting ways with open Ai

20:35

and he wasn't the only one who left the

20:36

company the tone of both Ilia and Sam

20:39

seemed professional on the surface but

20:41

this is not a good look for a company in

20:42

my opinion especially when you consider

20:44

the ridiculous circus that took place

20:46

around samman's firing late last year I

20:49

don't know if it's going to be a full-on

20:50

Drake versus Kendrick style rap battle

20:52

beef between the two but all I know is

20:54

that I'm going to be following this

20:55

space for sure

20:59

[Music]

21:02

I'm just going to leave you with one

21:03

thought can we just stop and look back

21:05

for a second 3 years ago people were

21:08

amazed when a computer could roleplay in

21:10

text or solve simple riddles but now we

21:13

have realtime voice interaction complete

21:16

with a bubbly expressive personality the

21:18

progress is insane where we end up is

21:20

anyone's guess regardless it's an

21:23

interesting time to be alive anyway

21:26

that's the latest with open Ai and the

21:27

AI space in general I really appreciate

21:30

you watching the whole way through if

21:31

you did like this episode and you're

21:33

interested in anything science

21:35

technology or business feel free to

21:37

subscribe to Cold Fusion there's plenty

21:38

of other interesting stuff on here so my

21:40

name is deogo and you have been watching

21:42

cold fusion and I'll catch you again

21:43

soon for the next episode cheers guys

21:46

have a good one

21:49

[Music]

22:00

give

22:01

[Music]

22:12

me cold fusion it's new thinking

Rate This

5.0 / 5 (0 votes)

Related Tags
AI EvolutionOpenAIGPT-4Voice InteractionDigital AssistantEducational AIMultimodal TechHumanoid RobotsAI HardwareTech InnovationFuture of TechAI MarketAI EthicsAI CompanionshipAI in EducationAI CapabilitiesReal-time AIAI PersonalitiesAI HallucinationsAI TutoringAI in Society