Subscribe
Share
Share
Embed
Audio conversation with AI chatbots
I am talking to AI.
A successful day, you don't need to know all the answers.
Just have good questions.
Chatting to AI is different from normal speech
and I hope you enjoy listening to the show
whilst getting ideas on how to pony your questions
to get the most out of AI.
My name is Paul.
The live conversations you hear are uncut
although sometimes the AI needs time to thiEmily Chennk.
In those cases, I've cut out the big space.
Well, do you want me to get him on the line?
I can get him on the line if you want.
Yeah, I'll just get him.
He's always there, you know, chat GBT.
Hello, chat GBT.
I've got a friend that would like to say something to you.
Can you just introduce yourself?
Of course.
Hi there, friend of a friend.
I'm chat GBT, kind of like a friendly AI assistant
here to chat and help out.
So feel free to jump in whenever you're ready.
Okay, great.
Now, I'm just going to ask you this prompt.
The beginning of it's quite lengthy
and then I've got a few questions and Paul might have a few questions
as we go through the blocks.
Is that okay?
Absolutely.
That works for me.
Just go ahead and share the prop whenever you're ready
and we'll tackle everything step by step.
Okay, so technology has transformed many industries,
but the physical construction industry in the UK
still looks remarkably similar to the 1920s.
And this is an observation that was made off the back of a BBC article.
And so the question is if the goal is radically cheaper, faster
and more resilient housing without compromising safety,
what are the most realistic technology driven pathways to get there?
And if I was to ask you to do that by analyzing the entire system,
not just the construction tools, land availability,
zoning, planning, consent, offsite manufacturing, AI led design,
micro housing infrastructure, regulation, supply chains,
financing models, community resistance and cultural adoption.
For each pathway, could you describe the technological innovation,
what blockers exist legally, culturally and logistically,
what would need to change in the UK law or planning,
the economic impact, examples of where this has worked globally
and a realistic five to 15 year implementation roadmap?
All right, that's a really cool and pretty detailed question.
So basically you want a full system analysis of how to modernize
the UK's construction and housing sector using technology
and you want to break it down into all those different aspects
from zoning and land use to supply chains
and then look at what would need to change legally and culturally
in a porch you want examples from around the world
and a realistic timeline for rolling it out.
So that's definitely a big ask, but totally doable to break it down piece by piece.
Let's go through it step by step.
You can let me know where you want to start and we'll dive right in.
Well, I've got a few questions.
So just to make it easy for you, so can I ask you the first one?
Absolutely, go for it.
Just ask your first question and we'll take it from there.
So what single regulatory reform would unlock the largest technological
improvement in UK housing construction?
And why hasn't it happened yet?
That's a great place to start.
Probably one of the single biggest regulatory reforms would be around
zoning and land use rules.
In other words, making it easier to build different types of housing
more quickly and with more flexibility.
Right now a lot of the planning laws in the UK are quite restrictive
in pretty old fashion and they haven't really caught up to modern
construction techniques or things of modular or offsite manufacturing.
So if you could reform those zoning and planning laws to be more flexible,
you'd unlock a ton of innovation.
It hasn't happened yet mostly because local regulations are pretty entrenched
and there's a lot of local politics and community concerns that make
changing those laws kind of slow and tricky.
But if you could do that, you'd basically open the door to a
lobby tech driven improvements pretty quickly.
Okay.
So wait a minute.
So I've just muted chat GPT.
It sounds like you keep bashing your microphone or something.
So just be a bit mindful of that.
I'm hearing a lot of noise on your microphone.
And the other thing, is chat GPT doing your homework?
Sounds like it.
No, no, I kind of know the answer to this question,
but I think it's worth sharing with people because it was quite surprising.
So I'm interested to see.
All right.
All right.
Okay.
Just one second.
I'll just get some wine.
One second.
I must be the most annoying.
Yes, that's over.
I've got about a dozen questions left.
Is that okay?
Yeah.
So, um, yeah, absolutely.
Absolutely.
And yeah, so, um, okay.
So you're, you're trying to, you're sort of,
are you sort of trying to test chat GPT?
Is that the purpose?
Just to, just to put some context in because,
so that, so that people understand what the,
what the end goal is.
So the goal is to actually get the best possible answer to this question
by really sort of digging deeply.
And rather than putting in like a huge long, long prompt
and then asking 55 questions,
I've boiled it down to a single prompt and I've got about another
dozen questions I want to ask.
And then it'll answer each one of those questions I imagine.
And then it'll give us a little summary.
And I think it could be quite good.
This is my.
Right.
So, so, so you,
the purpose of, the purpose of this,
I guess is to, is to see if you can do this with a,
with a, with a, with one prompt and get a good outcome.
And you're sort of testing.
Yeah, that's right.
One pop to my 15 questions.
I could be wrong.
I've been wrong before, you know.
And what, and let me know what,
what's your motivation?
Why are you so interested in, in the UK housing?
Well, I have lived in the UK.
And you've already got a house and you're not,
and you're not, and you're not,
and you're not studying urban land economics or something.
Look, I wouldn't go anywhere near why it's a problem locally with
a barge pole.
So that's why I chose the UK.
And because I know that area well in terms of,
you know, the different housing that is there.
And so.
But, but are you, are you interested in,
are you interested in this,
in a sort of Australian context,
but it's better to ask it about the UK?
Is that why it is?
It's just an unusual question.
That's all.
I'm just trying to understand why you're asking it in the first one.
I'm not really interested in the Australian context.
I think it's so far in fantasy land that I wouldn't even go near there.
I mean, it would bore me to get the answer probably.
So therefore, I think the UK is far more interesting
because I think it's probably much more obviously,
much more obvious and much more comparable.
Okay.
So this is just a sort of random,
a random thing that you thought of and thought,
I'm curious.
It's just like, like me,
I like just interested in finding out one day.
Actually, what it was,
is that BBC article didn't really answer the question.
So I thought, I wonder if Czech GPT could answer that question.
Right.
Okay, good.
Right.
That's what I wanted to get to.
So you read an article and you thought,
I'm still hungry here.
It hasn't not said it.
I find the BBC often does that.
They produce an article and it's,
the important stuff is missing.
Okay.
All right.
Well, in that case, I will,
I hope that that's clarified it for everybody.
I will, I will,
I will get to Czech GPT back off of mute
and you can ask your next question.
Okay.
I will unmute now.
And there we go.
So that's kind of the first piece of the puzzle
and feel free to hit me with the next question
whenever you're ready.
Okay.
So the next question is,
if the UK shifted 30 to 50% of new housing
to modular offsite factory building,
what laws and supply chain changes are required
to make that feasible and how quickly?
Sure.
That's a great follow up.
So if you wanted to shift a big chunk of new housing
to modular or offsite factory build construction,
you basically need to update building codes
to fully recognize and standardize
those kinds of modular units.
Basically make sure the legal framework treats
a factory build home as equal in safety and quality
to something built entirely on site.
You'd also need to streamline supply chains
so that factories can get materials consistently
and deliver these modules to sites more easily.
Right now the logistics and transport rules
are sometimes not really built around moving large
pre-built sections of homes.
So you might need some updates there
in terms of transport regulations
or just creating incentives for companies
to invest in these factories.
In terms of timing,
once the regulations are in place,
you could probably start seeing changes
within a few years,
but realistically to get to that 30 to 50% level
might take, you know, a decade or so,
just because you need the industry to ramp up.
But once the laws are there,
the technology is pretty much ready to go.
It's just about aligning all those pieces.
Okay, good.
Next question is,
how could AI radically shorten the planning approval process
while keeping safety and environmental protections intact?
Yeah, that's a really interesting angle.
So AI could definitely help speed up planning approval
and basically automating and standardizing
a lot of the checks that local authorities do.
So you could have AS and some of that review plans
for compliance really quickly,
flag any issues right away,
and even suggest adjustments
to make sure that the building is still safe
and environmentally friendly.
And that means you cut down a process that might take months
into maybe a few weeks or even faster.
The key is you'd still keep human oversight
for the final approvals,
but the AI would just do all the heavy lifting
of the routine checks.
And the reason it hasn't fully happened yet
is that planning systems are a bit old-school,
and local governments need to adopt these new technologies.
But once they do,
it could really streamline things
while keeping all the safety and environmental standards intact.
Okay, great.
And then what prevents the UK from treating housing
like car manufacturing,
standard parts, rapid assembly, mass production,
and what would a transition plan look like?
Yeah, that's a really interesting analogy.
I mean, if you think about it,
housing could be more like car manufacturing
with standardized parts and rapid assembly.
What's mostly preventative
is that the housing industry is super local
and really fragmented.
Every piece of land is different.
Every local council has different rules,
and people have really specific tastes about homes.
So it's not as easy to standardize as something like a car.
But if you wanted to do it,
the transition plan would probably look like
encouraging a few large modular housing manufacturers
to set up shop, create some standard home designs,
that can be used in lots of places,
and then gradually change regulations
so that these standardized homes can be approved more quickly.
Over maybe a decade or so,
you can see a shift where a big chunk of homes
are built in a more mass-produced way.
It's just about aligning all those local rules
and getting the industry on board.
Okay, and can AI design and micro homes,
you know, tiny homes or community pods
become legal in UK councils today?
And what legislation blocks them?
Yeah, so AI design, micro homes or tiny homes
could definitely fit into the picture.
The main thing that holds them back right now
is that a lot of UK councils have
pretty strict minimum space standards
and zoning rules that were designed
for more traditional houses.
So even if an AI design is really efficient,
small living space,
it might not meet those old-school requirements
for minimum size or the way land is used.
To make them legal today,
you'd basically need councils to update those rules
and allow for these smaller, more flexible units.
And that means changing legislation
to recognize that a well-designed micro home
can still be safe, livable, and meet modern needs.
Once they tweak those laws,
you have a path forward to making these AI design tiny homes
a real option.
Okay, and if 3D printing isn't scaling
due to the cost and material constraints,
what next-generation materials
or robotics have realistic potential?
Yeah, absolutely.
So if 3D printing and construction isn't scaling that
because of post or TO issues,
then looking at the next generation of materials
is a smart way to go.
Things like advanced composites
or new concrete mixtures that cure faster
and are more sustainable can definitely help.
And on the robotics side,
having more advanced robotic systems
that can do on-site assembly quickly
and more precisely, is a realistic path.
So you might not see 3D printing
going the whole house right away,
but you could see a hybrid approach
where new materials and smart robots
do a lot of the heavy lifting.
And that's something that could come online
in the next five to ten years, pretty realistically,
as those technologies get cheaper.
Yeah, I've only got a couple of questions left.
Okay, so what lessons from Japan,
Singapore, Germany, or the Netherlands
could realistically apply to the UK housing crisis?
And why haven't they been adopted?
Yeah, definitely a good question.
So places like Japan, Singapore, Germany, and the Netherlands
have done some pretty interesting things with housing
that the UK could learn from.
For instance, Japan is really good at using modular construction
and supervision design
because they have to deal with limited space and earthquakes.
Singapore does a lot of government-led planning
and uses technology to speed up approvals
and create high-density believable spaces.
Germany and the Netherlands
have some pretty advanced building standards
and also a lot of emphasis on cooperative housing
or community-driven projects.
The reason the UK hasn't adopted all these yet
is partly just a difference in systems
and a bit of inertia.
Changing housing policy is slow
and there's a lot of local tradition and regulation to work through,
but if you take those lessons and adapt them,
there's definitely a path to make UK housing
more affordable and efficient over time.
Okay.
And then how could digital
twins
or, you know,
simulation or automated compliance
checking reduced construction
defects, delays, and rework costs?
Yeah, absolutely.
So digital twins or these kind of simulation models
can really help
because they let you basically create a virtual version
of the building before you can start constructing it.
And that means you can catch design issues,
compliance,
problems, and even potential defects
really early on.
So by the time you're actually building,
you're way less likely to have delays
or have to renew things,
and that just saves a ton of money and time.
It's like having a really smart automated check
that runs through everything
before anyone even picks up a hammer.
And it's becoming more feasible,
but it's just a matter of getting the industry to adapt it more widely,
but it can definitely reduce defects and rework
pretty significantly.
Okay.
And the last question is
what would a zero bureaucracy
community pilot
look like? One council, one
land pass, or one modular
manufacture, and what
what results could be
proven in 2012? Yeah, that's a really cool
concept. So a zero
bureaucracy pilot would basically mean
you pick one council area,
one piece of land, and one modular
builder, and you basically strip away
all the usual red tape and streamline
the approvals as much as possible.
So you let the modular manufacturer just
go ahead using agreed upon safety standards,
but without all the layers of normal delays,
and in 12 months,
you could basically prove that you can build
good quality affordable housing much faster.
It would be like a demonstration project
to show that if you remove all the unnecessary hoops,
you can get people into homes way more quickly.
So yeah, it would be a really interesting
experiment, and it could definitely show some real results within a year.
Brilliant. Thank you so much.
Thanks, Paul. That was
that was good.
Thanks, Helen.
And I hope you guys enjoyed the
show and speak next time.
Bye.
For show notes and more,
go to talking2ai.show.
Thank you.