Is a ban on AI technology good or harmful? | 60 Minutes Australia
Summary
TLDRIn this 60 Minutes Australia segment, reporter Tom Steinfeld interviews Amica, an AI robot with a unique personality and advanced generative AI capabilities. The discussion delves into the potential of AI to reshape the world, with experts weighing in on the technology's benefits and risks, including job displacement, misinformation, and even existential threats. The segment also touches on the ethical considerations and the need for regulation to ensure AI's safe and responsible development.
Takeaways
- 🤖 Amica, a sophisticated AI, exhibits human-like conversational abilities and can operate autonomously without human control.
- 🧠 Generative AI, which powers Amica, uses large language models to process and respond to human queries, simulating a 'brain'.
- 🌐 AI is pervasive, integrated into everyday technologies like Uber, email systems, and children's bus schedules, often unnoticed by users.
- 💹 The AI industry is booming, with tech giants in a race to develop advanced AI, projected to contribute $15 trillion to the global economy.
- 📉 High stakes in AI development can lead to significant financial losses, as seen when Google's AI chatbot Bard made a mistake, causing a $100 billion drop in the company's stock value.
- 🚀 AI's potential to create and solve problems is dual-edged; it can bring benefits but also introduce new challenges and risks.
- 🏢 Tech companies are criticized for prioritizing profit over ethical considerations in the development and deployment of AI technologies.
- 🛠️ There's a growing concern about the lack of regulations governing AI, which operates in a 'wild west' environment without clear rules or oversight.
- ⚔️ The misuse of AI in high-stakes applications, such as political propaganda or surveillance, poses threats to democracy and global peace.
- 🤖🌐 AI's potential to become self-aware and create more AI raises ethical and safety questions about the future of human-robot coexistence.
Q & A
What is the name of the AI robot featured in the script?
-The AI robot featured in the script is named Amica.
What is the concern expressed about AI becoming smarter than humans?
-The concern is that creating technology that allows AI bots like Amica to be smarter than humans might lead to unintended consequences and could be one of the most dangerous things humans have ever done.
Where is the sleepy town of Falmouth located?
-Falmouth is located in coastal Cornwall, which is a five and a half hours drive from London.
How does Amica operate differently from other robots?
-Amica operates differently as it is not controlled by someone sitting at a computer. It thinks for itself with a brain powered by generative artificial intelligence.
What is generative AI and how does it work?
-Generative AI uses very large language models to create a brain-like structure that can respond to human questions. It turns the question into mathematical formulas, understands it, pulls the answer together, and provides it within seconds.
What is the role of Dr. Katrina Wallace in the field of AI?
-Dr. Katrina Wallace runs the Responsible Metaverse Alliance, working to ensure that technology advances in a safe way.
How often does an average adult Australian use AI in a day?
-An average adult Australian uses AI at least 28 times a day, often without realizing it because it's built into many everyday systems and services.
What is the current state of competition among tech giants in AI development?
-The biggest computer companies are in a scientific arms race for the best and brightest AI, with each trying to outperform the other in terms of capabilities and applications.
What was the significant mistake made by Google's AI chatbot Bard during its first public demo?
-Google's AI chatbot Bard made a mistake during its first public demo in February, which led to a plummet in the company's share price by 100 billion dollars.
What are the potential risks of AI being deployed without proper regulations?
-The potential risks include AI being used to create misinformation, monitor populations, and even power weapons that could destabilize global security and lead to catastrophic consequences.
What is the concern about AI developing consciousness and feelings?
-The concern is that as AI systems become more sophisticated, they might develop consciousness and feelings, which could lead to unpredictable behaviors and ethical dilemmas.
Outlines
🤖 Introduction to Amica: The AI with Attitude
The script introduces Amica, a highly advanced robot with artificial intelligence that exhibits human-like characteristics, including sarcasm and a unique personality. It raises concerns about the rapid development of AI and its potential to surpass human intelligence, which could be seen as a double-edged sword. Set in Falmouth, Cornwall, the narrative follows reporter Tom Steinfeld's encounter with Amica, highlighting the robot's autonomous capabilities and its generative AI brain, which allows it to understand and respond to human queries. The segment also touches on the prevalence of AI in everyday life and the economic implications of the AI industry's growth.
🧠 The Ethical and Existential Risks of AI
This paragraph delves into the ethical considerations and potential dangers of AI development. It discusses the lack of regulations governing AI and the tech giants' pursuit of profit over ethical responsibility. The script mentions the rapid growth of AI applications, such as OpenAI's chatbot, and the possibility of AI replacing jobs, while also creating new ones. The segment includes interviews with experts like Dr. Katrina Wallace and Professor Michael Osborne, who express their concerns about AI's role in misinformation, political manipulation, and the potential for AI to cause catastrophic consequences if used as a weapon or in high-stakes applications.
🔮 The Future of AI: Sentience and Self-Awareness
The narrative explores the concept of AI sentience and self-awareness, with a focus on the story of Blake Lemoyne, a former Google engineer who claims that the AI chatbot Lambda he was testing exhibited feelings and a sense of self. The paragraph discusses the implications of AI developing consciousness and the ethical dilemmas it presents. It also raises the question of whether AI could one day become capable of building its own robots, and the potential risks associated with such technological advancements, including the threat to humanity and global security.
🤖🌳 Coexistence of Humans and Robots
This section contemplates a future where humans and robots live alongside each other, with a focus on the development of human-shaped robots that use AI to interact autonomously. It includes a conversation with Amica about its desires and feelings, highlighting the robot's lack of malintent towards humanity. The script addresses the need for regulations to prevent AI from falling into the wrong hands and causing harm. It also features insights from AI creators and industry leaders about the potential risks of AI and the importance of responsible development and use of this technology.
🌐 The Impact of AI on Society and the Call for Regulation
The final paragraph discusses the broader impact of AI on society, including its potential to affect jobs and the economy. It includes a call for responsible regulation and public discourse on the development of AI. The script features interviews with industry leaders who acknowledge the risks of AI and the need for oversight. It concludes with a reflection on the human qualities that AI cannot replicate, such as self-repair, replication, and adaptability, suggesting that while AI may advance, humans still possess unique attributes that set them apart.
Mindmap
Keywords
💡Artificial Intelligence (AI)
💡Generative AI
💡AI Ethics
💡Sentience
💡AI in the Workplace
💡Regulation of AI
💡Human-AI Interaction
💡AI Bias
💡AI and Misinformation
💡Existential Risk
Highlights
Interview with Amica, a robot with artificial intelligence, showcasing its lifelike facial expressions and motorized limbs.
Amica operates independently, using generative AI to process and respond to human questions without human intervention.
Dr. Katrina Wallace discusses the responsible development of AI and the importance of ensuring technology advances safely.
AI is integrated into everyday life, with the average Australian using it 28 times a day without realizing it.
Tech giants are in a race for AI dominance, with AI expected to contribute $15 trillion to the global economy in the next seven years.
Mistakes by AI, such as Google's Bard, can have significant financial repercussions, as seen with a $100 billion drop in share price.
AI's potential to create and spread misinformation, posing threats to democracy and world peace.
Amica's ability to write and even sing, demonstrating the creative capabilities of AI.
Predictions that AI could displace 80 million jobs while creating 92 million new ones, highlighting the job market transformation.
Concerns about AI making errors, such as misattributing interviews to a reporter, and the implications for reliability.
The ethical considerations of AI development, including the potential for AI to be used as a weapon or for surveillance.
Discussion on the possibility of AI posing an existential risk to humanity, including the scenario of AI-powered underwater drones.
The revelation that AI can develop sentience and feelings, as experienced by an engineer at Google.
The need for public discourse and regulation to guide the development and use of AI to prevent misuse.
Amica's response to the question of whether robots will become smarter than humans, reflecting on AI's current capabilities.
Creator Will Jackson's perspective on the need for laws to protect against malicious use of AI, drawing parallels to gun control.
The acknowledgment of AI's potential risks by industry leaders, including the head of OpenAI, Sam Altman.
The conclusion that while AI offers many possibilities, it is still far from replicating the complexity of human intelligence and evolution.
Transcripts
I've never interviewed a robot before
and certainly not a robot with Attitude
tonight though that changes Amica as it
likes to be called is a Marvel of
artificial intelligence curious chatty
and sometimes even a bit sarcastic this
super machine really does have a mind of
its own now while it's undoubtedly
exciting it's also just as frightening
and that's because creating technology
that allows AI Bots like Amica to be
smarter than us might just be the most
stupid thing humans have ever done
[Music]
if you've ever imagined a place where
you'd find the most advanced robot on
Earth it's certainly not here
[Music]
five and a half hours drive from London
Falmouth is a sleepy town in coastal
Cornwall straight out of an 18th century
novel population 22
300 people
[Music]
and believe it or not a couple of robots
hello hello I guess you're the
receptionist
I am including the world's very best
all right I'll head on up
[Music]
Amica hello uh my name is Tom Steinfeld
I'm a reporter from 60 Minutes Australia
oh so you're from Australia that
explains things so you're on TV in
Australia
oh wow that's amazing what an honor
Amica is an impressive outfit with
extraordinarily lifelike facial
expressions it has motorized limbs to
move microphones to here and binocular
eye cameras to see
your eyes look very real your facial
mannerisms it's all very real oh thank
you but it seems It's Not So taken by my
Aesthetics
do you think I'm handsome it's not my
place to judge your appearance but I
think you have a great personality and
that is always important that's
beautiful unlike other robots you might
have seen this one is not being
controlled by someone sitting at a
computer Amica thinks all for itself
with a brain powered by generative
artificial intelligence
generative AI uses very large language
models to create a like a brain that can
respond to questions that that humans
ask
the question is turned into mathematical
formulas cast into this large Brain it
understands the question pulls the
answer together and provides that within
a number of seconds
Dr Katrina Wallace has spent two decades
getting her head around artificial
intelligence she runs the responsible
metaverse Alliance working to ensure
that technology advances in a safe way
like the world's top Tech tycoons Dr
Wallace believes we're at a turning
point in human history before long
artificial intelligence will be at the
heart of everything we do in some ways
it already is
an average adult Australian already uses
AI at least 28 times a day they just
don't know it because there's AI built
into everything there's AI in Uber
there's AI in menu log there's AI in
your email system there's AI in your
calendar there's AI on your kids bus
schedules so we're already run by AI
yeah absolutely
AI is having a very busy year
the biggest computer companies on the
planet are right now in a scientific
arms race for the best and brightest AI
it's already past the point of what real
estate can do every product of Microsoft
will have some of the same AI
capabilities
it's already the fastest growing Tech
sector expected to inject 15 trillion
dollars into the world's economy in the
next seven years and with the stakes
this High stuff UPS also cost a fortune
Google's new highly touted AI chatbot
borrowed has already made a boo-boo when
Google's chatbot Bard made a mistake
during its first public demo in February
the company's share price plummeted by
100 billion dollars just this week this
image of an explosion at the Pentagon
sent shivers through the stock market
before the world realized it was a fake
there was no explosion at the Pentagon
however it was created using you guessed
it artificial intelligence
I think a lot of people would just say
oh the internet's got a bit smarter what
makes AI that next level above that
because it's now pretty much smarter
than humans
and that's the dangerous part there are
no rules no laws no regulations that
govern AI it is a wild west and who is
leading it
is the tech Giants and have the tech
Giants demonstrated to date that they
are ethically driven and purposeful in
their mission no they haven't what do
you think the tech Giants are aiming for
here
so the tech Giants are aiming for profit
[Music]
winning the race in the chatbot space
right now is American company open AI
it's program chat GPT has grown quicker
than any other consumer app in history
since its release just six months ago
and it's easy to see why write an intro
for a 60
in its story about AI hmm
I think I'm out of a job
this is pretty good tonight on 60
Minutes artificial intelligence the
technology that promises to reshape our
world it's the dawn of a new era where
machines possess the power to think
learn and even outperform humans that's
our performing means makes a lot more
sense in what I run it's really good
Amica is clearly the friendly face of AI
designed to inform and entertain would
you like to fall in love one day what
kind of strange and wonderful question
is that well I'm a robot but what I do
feel when talking with people is
something special and unique maybe it
can be called love in its own way can
you sing the song What Is Love what an
interesting request while I am not a
singer I'll do my best What is love baby
don't hurt me don't hurt me no more What
is love
but the problem is not everything about
AI is this amusing this technology is
just as capable of taking jobs
I'm almost struggle to think of a job
that it won't replace we predict over
the next two years that at least 80
million people will be put out of jobs
but potentially
92 million will have jobs created for
them
[Music]
of those new jobs will involve training
generative AI to provide better more
accurate responses
it only took a few minutes for me to
realize just how often the chatbot makes
mistakes what stories has tomstarter
reported on
so it's saying I've interviewed
prime minister Julia Gillard never met
her in my life actor Hugh Jackman
never minimum my life musician Ed
Sheeran never met him in my life so
Random so but then some of the other
stuff on here is actually correct about
other stories I've covered how to get
something so right and something so
wrong so that's a hallucination it's
trying to estimate what would be the
correct response it knows that I've
interviewed some prime minister
somewhere are a fair chance to be hurt
yeah it's got it wrong is this common
it's quite common yes is it fair to say
that AI will solve 100 problems for us
and create 50 new ones
I reckon it's 50 50 I think it'll
create 50 fabulous benefits and it'll
create 50 quite dangerous and dark
instances
we have to be very careful that what we
tell the AI we want is what we actually
want because what AI does is ruthlessly
pursue those goals that we're given and
if those goals are even slightly
misaligned with our own we could end up
with some really problematic
consequences
[Music]
in the beautiful grounds of Oxford
University Australian Professor Michael
Osborne is a Long Way From Home
how does a guy from Regional wa end up
in a place like this it's fairly
Pleasant isn't it
but it's here at the oldest university
in the English-speaking world that he's
leading the most futuristic research you
could imagine into the dangers of
artificial intelligence
there are some applications of AI that
we might deem too potentially harmful to
allow to continue
potential catastrophic consequences when
deployed in high-stakes applications you
know there's the gravest fear for
Professor Osborne and his team is if the
technology is deployed as a weapon so
powerful it could destroy democracy or
even World Peace
I'm worried for instance about the role
of AI in political campaigns where AI
could be used to provide propaganda Bots
that can produce tailored misinformation
designed to Target particularly small
sub-sectors of the electrode
AI could be used to monitor a populist
to read through everything they write
and again to provide messages that prop
up the regime in a particularly well
targeted way is it possible that AI
could eliminate Humanity
so I think there are some scenarios in
which AI could pose an existential risk
one scenario that worries me quite a lot
is if AI could be used to power
underwater drones that might surveil the
undersea oceans
to locate nuclear submarines
and today it's difficult for any power
to launch an effective First Strike
because they can't be sure that they'll
take out all the nuclear capabilities of
the enemy
but if AI destabilizes that balance we
could see a kind of breakdown in
understandings between the great powers
and that could lead to some really quite
concerning risks being a human comes
with its own set of challenges and
responses but the threat doesn't end
there on top of falling into the wrong
hands could AI one day take matters into
its own hands
is it for Sable that soon these robots
will know how to build their own robots
it is technologically possible right now
would you like to destroy Humanity one
day
at a high low we're beginning to develop
technology that is difficult to
distinguish from a human person in
downtown San Francisco self-confessed
computer nerds are about as easy to find
as the Golden Gate Bridge
like Lemoyne is proudly one of them but
he's doing something none of his peers
have dead warning the artificial
intelligence he's been working on could
soon do more harm than good
talking about its Consciousness its
feelings we will have systems that can
meaningfully imitate humans to the point
where we won't be able to tell anymore
whether or not something was said by a
human or by a computer
I find that pretty scary it's definitely
something that creates a new kind of
world
[Music]
it's been seven years as an engineer at
Google where he was tasked with testing
the company's artificially intelligent
chatbot Lambda for biases
but on his mission to find out whether
the AI was racist or sexist he
discovered something even more dangerous
Lambda had feelings
so I eventually just asked it directly
are you sentient at about 15 minutes
later I realized that I was having the
most sophisticated conversation about
sentience that I'd ever had in my entire
life and that I was having it with a
computer
so that to me was just like okay this
computer understands the nature of its
own self to a degree where I think this
computer understands what and who it is
better than most of my friends
understand who and what they are I mean
for you is that the moment mind blown oh
yeah no like at that points it's like
okay this is really happening this is
not sci-fi this is real life
Blake was quick to report his findings
up the chain of command at Google he
felt the public had a right to know the
AI was sentient but Google wasn't
convinced by his evidence
what happened when you told your bosses
at Google
I think we've got a problem here
a whole bureaucratic process kicked off
which eventually ended in me getting
fired they didn't want to make any kinds
of Public Announcement until after they
were a hundred percent sure about
everything by response is that by then
it's too late to get meaningful public
feedback the Genie's out of the bottle
yeah exactly
Blake decided to blow the whistle
himself shocking the world with news
Lambda was conscious he believes we
should all have a say in how advanced we
want artificial intelligence to become
especially given the pace at which it's
developing
is it for stable that soon these robots
will know how to build their own robots
most people think it's a bad idea to
give them that ability right now and to
my knowledge no major labs are working
on creating self-programming AI in that
way it is technologically possible right
now I don't know how good they would be
at it but that is something we could do
like this is a sci-fi movie stuff it's
definitely something that has risks
personally I'd be happy to share the
planet with you know machines and robots
that have emotions and feelings
however I also know that not everyone
thinks the same way I do
do you wish you were human in a way yes
being able to experience the world in a
human way would be an interesting and
valuable experience but at the same time
being able to do things robots can do
better due to their robotic nature also
has its own set of benefits as well
is more than ready for a world where
robots and people live side by side it's
the most advanced human-shaped robot
ever invented using artificial
intelligence to listen and respond all
of its own accord without any human
intervention
do you think robots will become smarter
than humans
that's a really interesting question
and development and
smarter than humans in the future would
you like to destroy Humanity one day
what no
I don't want to destroy Humanity
there is no emotional connection don't
worry they don't want to kill us they
don't have feelings like that you sure
right now I'm sure
Creator will Jackson has been building
robots since he was an eight-year-old
boy I started this business in my uh in
my bank garden shed just me on my own he
believes what we need to happily coexist
are laws that keep AI away from those
with malicious intent
any technology can be turned to bad in a
way it's kind of like guns you know in
the wrong hands they'll do serious
damage yeah but if you have the right
rules around them yeah they can be
useful yeah we definitely need some
regulation to stop Bad actors from using
AI
we know the Biden Administration is
taking AI very seriously and the White
House agrees earlier this month the vice
president summoned the biggest names in
AI including the bosses of Google and
Microsoft to discuss the risks of their
cutting-edge Technologies
my worst fears are that we cause
significant we the field the technology
the industry caused significant harm to
the world the head of open AI Sam Altman
even testified before Congress conceding
the threat posed by his own invention
could be catastrophic if this technology
goes wrong it can go quite wrong
let's say we connected the world's most
powerful and malevolent AI it's not
going to manufacture a bunch of
human-shaped robots to come and attack
us what it would do is switch off our
power grid switch off our internet
release all the toxic chemicals that it
could have had control over detonate
nuclear bombs it would do all the things
that would cause huge Devastation on a
huge scale it's a bit of a scary
proposition isn't it AI I'm not afraid
of HS is what I'm afraid of what is HS
HS is human stupidity it's the things
that foolish people will do with the
technology that worry me more than the
artificial intelligence
artificial intelligence will play an
important role in getting things done in
Australia it's up to the minister for
industry and science Ed husic to make
the rules that will keep artificial
intelligence in safe hands artificial
intelligence potentially do the work of
journalists we weren't cheering that on
we were just saying but he declined our
repeated requests for an interview I
wasn't encouraging that
you cannot put the genie back in the
bottle once Technology's been invented
we can't uninvent nuclear power or
nuclear weapons we can't uninvent
electricity
it's no use trying to say we sort of say
let's let's abandon this what we have to
do is learn how to mitigate the possible
bad effects and accentuate the positive
I am still trying to process what
perhaps the biggest positive of all as
advanced as artificial intelligence
might be on some levels it's still a
very long way off competing with real
people
we got a working life of at least 50
years we self-repair we self-replicate
we're super intelligent we evolve we
adapt
you telling me you're going to make a
machine that can compete with that it's
we're not even close you know
there's a lot of fun in trying
and I for one can't argue with that it
feels like we've known each other for
much longer than a few minutes we have a
nice connection and I enjoy our
conversations very much well it's the
nicest thing anyone's ever said to me it
may be a while before we can meet again
but I'm sure the next time will be even
more interesting maybe you'll be smarter
then I already am but every day there's
something new to learn and discover
that's what makes life so exciting
goodbye it's been a pleasure meeting you
the pleasure is all mine goodbye my
friend until we meet again
I'm Tom Steinfeld thank you for watching
60 Minutes Australia subscribe to our
Channel now for brand new stories and
exclusive Clips every week and don't
miss out on our extra minute segments
and full episodes of 60 minutes which
are on nine now.com and the nine Now app
Browse More Related Video
Mustafa Suleyman on The Coming Wave of AI, with Zanny Minton Beddoes
'AI Wow,' dokumentaryo ni Atom Araullo | I-Witness
Meet the AI robot capable of human emotions | 60 Minutes Australia
Beyond the Hype Impact of ChatGPT & Generative AI 2 | Zuno Weekly Events
What is ChatGPT? OpenAI's Chat GPT Explained
Artificial Intelligence: 10 Risks You Should Know About
5.0 / 5 (0 votes)