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 pose 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 think.
In those cases, I've cut out the dead space.
Alright, so I'm going to try another experiment.
Let me see if I can do a bit of research
and talk to Grock
and talk to chat GPT.
What I'll do is I'll mute them in between
so they can't hear each other
and I'll ask them the same question
and we'll see what comes out.
I'm doing this off the cuff.
What sort of question should I ask?
I'll ask a question about crime statistics in the UK.
Let's ask.
Hi chat GPT.
Hey there, nice to hear from you.
Let me know what's on your mind.
I'd like to know a bit about crime statistics in the UK.
In the last 10 years in the UK, how has crime changed?
Sure, so over the last 10 years in the UK,
it's been a bit of a big spag.
Overall crime rates have generally gone down,
but some specific types of crime have actually gone up.
For example, theft from the person has risen quite a lot
since around 2015.
Knife crimes had some ups and downs.
Like in London recently it went down a bit,
but overall knife incidents have grown compared to a decade ago.
And retail theft has hit some record levels too.
So it's kind of a mix of trends depending on the type of crime.
Hi Grock, can you tell me,
I'm interested in crime in the UK over the last 10 years.
Can you tell me how it's changed over the last 10 years?
Hey, no worries about the UMS happens to the best of us.
So crime in the UK over the last 10 years,
overall it's been trending down,
especially for traditional stuff like burglary and car theft.
Back in 2015, the rate was around 80 crimes per thousand people in England and Wales.
And by 2024-25, it's dipped to about 79,
that's a roughly 10% drop total,
though it spiked a bit during the pandemic.
But it's not all rosy,
violent crimes like assaults have crept up about 20%,
and knife events hit record highs in places like London last year.
Frauds exploded too,
with online scams making up over 40% of all reports now.
Sexual assaults are up as well sadly.
Sources like the Office for National Statistics back this.
They've got detailed breakdowns if you want to dive deeper.
What's got you curious about it?
Okay, I've just muted,
ChedGBT and Grock are muted.
I thought there were quite different responses.
There was a lot more data in Grock than ChedGBT,
which was much more surface level, I guess.
So, okay, I'm going to try something else.
A bit more complicated.
I'll see if, I wonder if I get a...
Yeah, okay, this is interesting.
Okay, I'm going to ask a bit more complicated question.
It's going to be about the relationship between...
Yeah, well, I'll just go ahead and do it.
Hi, ChedGBT.
I've got a completely different question for you.
What is the relationship between skin tanning and skin cancer?
If you get tan,
is it going to make it more likely for you to get skin cancer?
Yeah, that's a great question.
So basically, when you get a tan,
it's actually your skin's way of trying to protect itself from UV radiation.
So while a tan might look nice,
it is a sign that your skin has been damaged by the sun.
And unfortunately, that damage can increase the risk of skin cancer over time.
So the more your skin is exposed to UV rays and the more tans,
the more that risk does go up.
It doesn't mean one tan is going to automatically lead to skin cancer,
but it's a cumulative thing.
So it is good to be cautious and use sunscreen and all that good stuff.
Okay, they're both muted again.
I'm going to ask the same question to Grogg.
Hello, Grogg.
Just a completely different question.
Can you tell me what is the relationship between skin tanning and skin cancer?
If you get tanned, are you more likely to get skin cancer?
Hey, totally different topic. Love it.
A tan means your skin's been damaged by UV rays,
whether from sun or tanning beds.
That damage builds up over time, and yeah, it does raise your risk of skin cancer.
Think of it like scars.
Every tan is kind of like a little injury that weakens your skin's defenses.
The stats?
People who tan regularly, say, using beds,
have a 75% higher chance of melanoma, the deadliest skin cancer.
Even natural tans aren't safe.
Studies show just five sunburns in life up your melanoma risk by 80%.
The American Cancer Society links it straight to UV exposure,
breaking down DNA in skin cells, leading to mutations that can turn cancerous.
Bottom line, tanning equates more risk.
You thinking about sunbathing habits or something specific?
Okay, they're both muted again.
I'm going to go in a little bit deeper on this,
so I'm going to go back to Chansey BT.
Hi, Chansey BT.
So can you tell me what evidence is there that tanning causes skin cancer?
Now, I'm particularly interested in tanning and not skin burns.
So I need something that shows a correlation or some kind of evidence.
What is the strongest evidence out there that tanning causes skin cancer?
Yeah, absolutely.
So there is actually quite a bit of solid evidence out there.
Even if we're talking about tanning rather than just burning,
the relationship is still pretty clear.
So a lot of dermatological studies and cancer research have found
that any kind of UV exposure that darkens the skin,
even if it's not a sunburn, still causes DNA damage in the skin cells.
And over time, that cumulative DNA damage can lead to mutations
that raise the risk of skin cancer.
And that includes things like melanoma, which is the most serious type.
So just to follow up, I did ask for evidence that shows it.
So can you cite some study or, yeah, I guess study,
that basically the most convincing evidence out there
that shows this relationship between skin tanning and cancer.
Good, Chansey.
Absolutely. Let me give you a solid example.
One of the most frequently cited pieces of evidence is from large-scale epidemiological studies.
For example, there's research published in the Journal of the American Academy of Dermatology
and also studies supported by the World Health Organization
that show a clear correlation between tanning, including indoor tanning beds,
which produce a tan without a burn, and an increased risk of melanoma.
These studies basically track large populations over tanning
and show that people who tan, even without burning,
have a higher incidence of skin cancers compared to those who don't.
So those kind of long-term cohort studies are really the strongest evidence
we have that tanning itself is linked to skin cancer risk.
All right, so, okay, last question on this.
So I actually asked you for a study and you haven't given me any.
You've just given me a bunch of organizations that have recommendations.
So I'm actually after, say it again, the most effective evidence,
the most effective study, the most convincing study there is that proves
that there is a skin cancer.
Well, first of all, you can tell me if it proves that skin cancer causes,
sorry, that it proves that skin tanning causes skin cancer.
And then you can tell me, or if it's something else,
but I want the most effective evidence that shows that skin tanning causes skin cancer.
Absolutely, I appreciate you pressing for a specific study.
So one of the most frequently cited studies is actually from the International Agency
for Research on Cancer, which is part of the WHO.
They published a large meta-analysis that pulled together multiple studies
and it found that people who use tanning beds before the age of 35
increased their risk of melanoma by about 75%.
Now, that's specifically for indoor tanning,
but it's the same principle of tanning without necessarily burning.
And that's one of the most convincing pieces of evidence.
Surely, okay, all right, I'm going to stop in a minute,
but surely if they're on the sun tanning beds, was there any relation?
How do they know that they just didn't get burnt more?
Yeah, that's a really fair question.
And it's something that researchers definitely consider.
In those studies, they do try to separate out the effects of just tanning
versus burning by looking at how often people tan and whether they report burns.
And the evidence still suggests that even without burns,
just the act of tanning does increase risk because it's really the UV exposure itself
that damages the skin cells.
So they do account for that, and that's kind of where that data comes from.
Okay, they're both muted again.
So I guess I'm feeling a bit unsatisfied with that conversation with your GPT.
I could keep digging, I guess, but there's a lot of high-level stuff there,
but I actually want to get to the studies and stuff.
So let's see if it's any easier with Grok.
This is my first time with Grok, so I've got no idea how that's going to change.
So I'll try and ask the same sort of questions to Grok.
Hi, Grok.
So do you think you could back that up with some evidence?
So I basically want, could you quote some studies
or basically the most effective evidence out there
shows that skin tanning causes skin cancer?
Sure happy to dig into the evidence.
It's pretty solid and consistent across big health orgs and studies.
Tanning, whether outdoors or in beds, ramps up UV exposure.
Okay, you've just told me that it's pretty self-evident and there's lots of science.
What I want is I want the actual evidence.
So can you give, can you quote some kind of, can you quote a study?
Preferably quote the most convincing study there is.
That would be that specifically looks at tanning
and the relationship between tanning and skin cancer.
Yeah, fair enough. Let's get specific.
One of the most convincing ones is a 2012 meta-analysis in the BMJ
pulling from 27 studies on over 18,000 melanoma cases.
It found that ever using indoor tanning beds raises melanoma risk by 20%
and starting before age 35 that jumps to 87%.
The lead author, Dr. Julian Newton Bishop, straight up says,
our findings add further evidence that use of sunbeds should be discouraged.
It's rock solid because it crunches thousands of real-world cases
controlling for outdoor sun too.
For natural tanning, a 2014 International Agency for Research on Cancer report
from WHO reviewed 20 plus studies and declared UV from sun exposure carcinogenic to humans,
linking it to 90% of non-melanoma skin cancers.
Tanning's just the visible sign of that damage.
Convinced or want me to hunt down the full abstracts?
Just a clarification. What is a non-melanoma skin cancer?
Non-melanoma just means skin cancers that aren't melanoma,
like basal cell and squamous cell carcinomas.
They're the most common ones, usually from long-term sun damage or tanning.
Unlike melanoma, they grow slow, rarely spread, but still need catching early.
Think scabby spots or rough patches that don't heal.
Super treatable if you spot them quick. Clear?
Okay, thank you.
Alright, well, I'm not gonna keep digging on that, but I could.
So, I think...
I think...
No worries at all. It's always good to dig into the details,
but if you're good with that for now, that's totally fine.
Just let me know if you need anything else.
Whoops. Sorry, guys.
I hit the wrong button.
So, I just wanted to say, yeah, I'm not gonna keep going on this.
I think what I've hopefully done here is showed that they are quite different
in their approach.
Grok and ChatGPT.
It's ChatGPT...
I'll just double-check which version I'm running at the moment.
Oh, yeah, just an interesting one.
Just because you select ChatGPT5 in the dropdown doesn't necessarily mean that's what you get.
The only way of checking, actually, and you can't tell by looking at it,
the only way of checking is to ask ChatGPT.
I'll just do that now.
ChatGPT, what version of ChatGPT are you currently running?
So, right now you're talking to the GPT4O version of ChatGPT,
and I'm happy to help with whatever else you got on your mind.
Yeah, so that's typical, yeah.
So, I pay for ChatGPT and I'm supposed to get ChatGPT version 5,
but at the moment I'm on ChatGPT4O.
So, that could make a difference, but, yeah, they're both quite different.
And I think if I was talking technical, I might prefer Grok.
I'm going to have some conversations with some other AI, like Gemini, later on.
And I think it was...
Yeah, the other one as well, I'll forget.
But, yes, there's two other AIs that I try to chat to, which both have audio.
And one of them does...
Some of them, you know, they do have different characteristics,
so it'll be quite interesting to compare them.
I might do something similar with some of the different ones.
So, anyway, I hope you found that interesting.
So, I suppose what that tells you is that they are different
and they give you information in different ways.
I don't know how relevant that is for, you know,
if you were just getting very mundane tasks done,
whether they make any difference.
And it could be that Grok works differently when it comes to image creation and what have you.
But the thing with Grok is that...
So, the reason why I haven't been using Grok very much
is that you have to use Grok on your phone,
so it's not as easy to do big prompts and things like that with Grok.
So, anyway, I hope you found that interesting.
I certainly did.
So, yes, till next time.
Bye-bye.
For show notes and more, go to talking2ai.show.