Welcome to Cloud Native Compass, a podcast to help you

navigate the vast landscape of the cloud native ecosystem. We're

your hosts. I'm David Flanagan, a technology magpie that can't stop

playing with new, shiny things. I'm Laura Santa Maria, a forever

learner who is constantly breaking production. All right, this

episode of Cloud Native Compass is all about AI, so

David decided to input a request rest into Chat GPT

for a sonnet about Kubernetes. David, why don't you start

us out? What did chat GPT say? In

digital realms where servers and sway a symphony

of nodes and rhythmic dance there lies a master

orchestrate and play Kubernetes, the captain of advance

its containers. Like actors on a stage, hold microcosms

of code's vibrant art with docker's grace they come alive

engage a ballet where technology takes part

scaling with grace like. Stars and boundless skies

replicas bloom weather at its will

resilient adheres to failure's cry yet presses

on each challenge to fulfill. Oh, Kubernetes, conductor

of the cloud, you orchestrate our dreams forever proud.

I can't believe I just read that.

So we have a guest on. So, JJ, can

you tell us who you are and what you do and

how it all works? The whole thing? All

of it? Yeah. Hi, JJ.

Asgard. I'm a developer advocate for IBM

now, and that means a lot. I wear a lot of hats.

That's what it boils down to. I kind of engage in

different organizations in different spaces, try to represent

developers and

their persona, I think is the project management term.

I'm trying to learn the vernacular. What can I say?

And right now, I'm focusing on

a product called Watson X, which is an AI

platform that's built off of open source, and I feel

like your audience would be interested in hearing a little bit about that.

Yeah, it's kind of an interesting topic to really bring

up. Now, I know that there's the Linux Foundation's,

AI and Data Foundation, and then there's obviously the

CNCF, which is another sub organization for the Linux Foundation.

So is Watson AI part of the AI data?

One. Is it the cloud native one? I want to dig

all the way down into this. Let's go for it.

Yeah, well, first of all, I got to be because I am an IBM er

and I have to get the branding correctly. Yeah,

it's Watsonx AI is

the official name of the AI platform for

Watsonx AI. We also have a couple of other

products coming down that do other portions that are required for

a real AI platform to work. I don't think I'm allowed

to publicly say those words quite yet. I don't actually know. But

the one that your community in general would be focusing

on, most likely is Watsonx AI. Now,

that one. So when you kind of tie that up

to the foundations and the organizations that

our industry uses, like LFAI and

things like that, what we have done as IBM is

kind of stepped into the LFAI to help build

the ecosystem for enterprise grade

level, an AI platform that allows enterprise

to be comfortable with using AI. I'm going

to just go into a quick little tirade about why, because you're probably like

JJ, why wouldn't any enterprise be happy with

this? Right? Yeah. Tell us a bit about why enterprises

maybe don't like AI. That's an interesting.

So. So there's this whole world right now of people being like,

AI is going to take our jobs,

right? Everyone knows this. Well, we can make fun of it,

but the truth of it is, as much as

people think Chat GPT or

all the other major disruptors out there have come into the

ecosystem and started giving you sonnets about Kubernetes,

which is actually surprisingly good. Yeah,

seriously, ask it for a song later. Okay. No,

anyway, and as much as people think

that's entertaining and interesting, when you start looking at

actual how our business is done, there isn't a

very good safe environment for this information.

So everything the Chat GPT gets, it learns off

of. So if you've looked at the Samsung for instance,

issue with people giving out the proprietary information

and then all of a sudden someone else gets that proprietary information about

the Samsung thing, hopefully we can find the link to

that. That is just a microcosm of

the problems when it comes to business. Because right now Chat

GPT is a complete and utter black box. There is no

way that the owners of Chat GPT or

OpenAI or Microsoft who has invested

billions into it, will ever give us the data

that Chat GPT has been built off of. And if you start going

down that train of thought, all of a sudden you recognize you're

giving all your proprietary information. You can't give your proprietary information, whether it

be a PDF of how your HR system works to the schematics

of a F 15. You can't use Chat

GPT with it because you don't know who's going to get it on the other

side. This is where Watson X comes into

play. A really great analogy for Watson X

versus the industry right now is Chat GPT is

Napster, watson X is itunes. If

you think of and you put it in that paradigm, all of a sudden things

start making a lot more sense on the enterprise level because now

you can go to banks and say, hey, we can give you a foundational model

that we can give you all the data that was built off of this. Obviously

with some money businessy stuff happening, right?

We're not going to just give it to you. Of course we need to build

the relationship, et cetera, but we can give you the

training on top of it, and then you can put your proprietary stuff on top

of that, so you can have the Chat bot that gives you that.

Turns out that Aetna is your insurance and he give you all the information you

need about Aetna or whatever, right. Which is, believe

it or not, something that's insanely

powerful. Right. So anyway, when you start

going down that track, you start seeing more things in that space.

You can go, David. I mean, I get asked more questions about open source and

AI, but you go next. Yeah, I just want to make sure

I understand the proposition correctly. Right, so you've done

this comparison, right? You're saying Napster versus itunes.

People use, say, chat, GPD and OpenAI to go and

ask any question because it's a model that is

trained on multiple billion of parameters, right. And all that information, like you

said, is a black box. We don't understand it. It doesn't really allow you

to, I don't know, dig into sort of niche subjects with

high cardinality. Yeah,

exactly. Watson X, I get to

decide what that data is, and I get to then

query it through a similar style interface. Is that what

Watson X would offer me as a developer? Like a model where I say,

here's, all of my data have my life, right? And then I can ask

it questions and it's going to give me answers. But if

that's true, which is cool, right? I have this little question where I'm like,

okay, is there a bias where it's only going to

confirm the stuff that I've given it in my data?

Is it going to be able to be slightly more objective? Can you feed outside

properties to augment and enrich? How does that all

work? That is a very great question,

and that's a natural progression, right? So let's go a

little bit deeper than the CIO CTO level

and let's go down to the senior.

You like that?

Yes. It's a very valid question. What is AI? A

good friend of mine, Carl, actually mentioned this the other day. What is

AI? It's just a yes man. Right. When you actually look at it, what is

AI? It takes percentages of the possible questions

you're asking. It finds the highest percentage of what you were looking for and gives

you that answer. That is what AI is. In a nutshell, it's a yes man.

It's a crony. Right? So what we need to do

is give accuracy to the crony to get the answers you were looking for very

specifically. Now, we have something called

foundational models, which is, I think there's four of them. I don't

know exactly what I'm supposed to say publicly right now, so I'm just going to

say there's four foundational models and they're all built

off of data that we

have agreed upon that are safe to

use. Now let's pivot quickly and talk about models in the

open source ecosystem. Models in the open source ecosystem.

Something called HuggingFace. If your audience doesn't know about it,

the easiest thing to describe hugging face as is the GitHub of

AI. It allows places to put

models up there that you can build off of previous models. They also give some

really nice I think the term is shims on

top of AI development work. So you don't have

to do all the stuff around it. You can write some very simple python to

be able to leverage stuff from hugging

face. Now, this is not

hyperbole. 95% of those open source models are

built off of something called literally the pile.

If you Google the pile AI, it is

a massive data set out there that is just like I

think 800 gigs last time I looked at it, that

people yeah, that is all just text and

information on the web that people just shoved together.

So LLMs or

linguist, language models. Language, language learning

models. Large language. Yeah,

large language model. Laura's language model. None of us

actually know. None of us know what this means.

Exactly. So 95% of

these LLMs out there are actually trained on

the pile. And trust me, Google it, it comes up in a

Wikipedia article. It's this whole big data set problem that they have. You've said

something right there, right? We have this open

source governed, centralized knowledge of Wikipedia.

Why is that not the base for these

models? Great question. Before we

get on that branch, let me finish what I was trying to talk about. Yes,

sir. The pile problem, which is

the pile isn't clean. There is a

lot of proprietary

pirated issues inside of

inside of the pile data. Inside of that there

are books that are completely ripped off. So when

you start looking the copyright law, right? And all of a sudden

finding out people have written and their books are in the

pile and the LLM is trained on their book without

permission, and they create something. Off of that. That brings

into some really interesting conversations about how our copyright law

works and then how with that too,

patent law works and then with that

licensing and all of a sudden,

what? Sort of looking for pyramid

scheme? Not only pyramid scheme, but the house of

cards that is our industry all of a sudden

starts falling apart. Because frankly

speaking, if we allow which right now, at this

exact moment in time when we're recording a federal judge and at

least the US government has said anything from

a AI that is created cannot be copyrighted,

right? That is this exact moment in time. I think that was literally

yesterday. But again, that's only here in the

US, right? And being

a US centric company at ABM, we obviously are paying very close

attention to this. This all brings up a whole conversation

of how do we keep going down this

path without possibly destroying our

industry, right? People joke about how we're barreling

forward to the end times, leveraging

AI and all that jazz, but when you actually look at

how we protect and can use the

entities that is governments to enforce yes, I have

not stolen your idea, and it is my right to sell this to people

for goods and services. If all of a sudden AI

can create all that stuff, and they create something very close to that and

they can start selling that as their proprietary thing, all of a

sudden businesses don't function. Right. As soon as

we get a real AI, that creates the next

I mean, if we call it

Taylor Swift bot, I don't know. You get what I'm saying? You

see, all of a sudden, the onion gets scarier and scarier and

scarier. So we have to build this

wall to make sure that the world we know

right now, which is going to change because we're going

to try to create avenues to be successful.

But if we're not, it's

scary, people. It's scary. Yeah.

So why not Wikipedia? Great question.

Yeah, I'm going to bring it back to a little bit of levity because otherwise

we're just going to go screaming down the black hole. We've already

passed the VP level. We've already passed the director. We're already into the thought

leadership engineering people, right? Thought leaders,

yeah. There you go. I do want to

say, well, at least from my understanding

of how Wikipedia works

and when if you parallelize it parallelize it?

Sure. With the pile, the amount

of errors inside of Wikipedia and

conflicting information, on top of the

ability to actually get the information out of Wikipedia and train it usefully,

there really isn't actually as much to get useful

information. It goes back to my simple example of a bunch of PDFs

to look for suggested areas to find stuff.

In my mind, that is the easiest path for most

people to grasp when it comes to understanding

the power of AI. Right? Now,

we've passed the whole if then statements of AI.

We've passed the whole ecosystem of

give me avocado chairs or

whatever from Dolly. Right now, we need to look at how we

can make our lives a little bit better.

There are LLMs or not even LLMs. I think they're

considered classification. But any point being is that you can shove a bunch of

PDFs into a model, then say, hey, I'm

looking for information about our

growth over the last two quarters. And maybe that's only in

a chart right inside of the PDFs of your business

logic. There are elements that can read all those charts and figure

out, hey, turns out growth over the last quarter is in this

graph, and it's over the last four years. This is the fourth spot

right here. Okay. It looks like it was 50%. It can respond back. It

looks like your growth was over about 50% referenced in this

diagram, in this PDF. Right. So it becomes like a

really great librarian if you think of it that way. And

then if you can tell that story to an enterprise.

Every enterprise, right, has massive amounts of PDFs of all their policies,

procedures, and everything like that. If you can create a

librarian, think of whatever Dystopian Sci-Fi that

has a librarian in it, which is always a thing.

If you can give that to an enterprise and say, I can give you a

way to do that with your trusted data that I know

will not leave our borders because that is core to our

business, maybe you should look into that.

But that also assumes that the librarian is not

making up data. I don't know if you heard about the lawyer

that asked for somebody to go through all of the legal

history for something and it turned out they made up, like the

LLM or the AI made up a

fake court filing to prove something and

judge caught it and it was a big deal. That's in the US.

Again, but still, I'm little worried about that

librarian not quite

being correct. But does this come down to

a misunderstanding of where people think AI is today?

When I speak to my wife, I speak to my family, I speak to friends,

and they're talking about Chad GPT, right? I mean, they're all trying it, they're all

playing with it because it's getting so much coverage. They don't understand the

generative part of it. They think it's giving them

knowledge. They don't know that it's just all made up. Now, we do

because we're in this industry, we follow the news, we read these stories,

but to most people it's a fact machine that's artificially

intelligent and is going to give you the correct answer.

Was the lawyer liable? Did they know it was fake? Did they not

verify it? Sure. But what did they expect from the AI?

And that's one reason why we have to get AI to cite the stuff, right?

That's not too far away to be able to like, where did you get this

information from? The natural progression is

citation and trust but verify. But

again, that also requires on the model that you've created and which model you've

chosen, which black box you've decided to do,

where the data is actually trained off of. Again, this all goes

back to the other problem that we don't talk about as an industry. And

as soon as you start playing more in the space, you recognize

that it's not the LLM or the model. I

know we're interchanging LLM and model.

I want to acknowledge first of all that that's wrong, right? But most people

have exposure to LLMs, so that's why it's

becoming like the Kleenex conversation. Again, I want to

acknowledge that that's wrong. There is very specific terms here, but just to

get there for the conversation, I want to make sure that that's clear. I know

what I'm talking about, but I'm even making this mistake.

The core value, the core problem of this whole narrative

is that we're talking about the compute, we're talking about the

compiler, we're not talking about the source code, which is the

data, right? And the data is what actually gives

the compiler, which gives you the answers of

the AI, the information we need to figure out a

way that we can have trusted data that exists in this

space that we know that won't create the court filing

or has the ability to create a court filing, right. And

we have that ability to have that conversation and trust that the AI does

that. But again, it goes back to the pile, which is a

bunch of untrusted data, where again, I'm going to be an

IBM shrill for a second and say we have engineers who are

dedicated to cleaning the pile. We actually have

humans that are going through the pile making sure that it is trusted

data to build our foundational models off of,

so we pull from the open source ecosystem. So we actually do have

that's the other part of IBM's whole model and why we have such

a good relationship. If you look into it with hugging face, specifically,

we've built partnerships directly with hugging face to pull

from the open source ecosystem because as Ibmrs know,

the open source ecosystem is going to drive the winds of the sail of the

ship or whatever enterprise statement you want to make

there of the industry. And

we acknowledge that. So we are spending a lot of time and effort in

building and building bridges to hugging face and taking the open

source stuff from hugging face and finding a way to make

it safe for enterprises to work. We have

whole teams of people inside of our research at

IBM that's all they do is they clean data.

I don't envy them at all because that's got to be boring.

But we do have these people who do it. And

I was at a training relatively recently about this, and

they were proud because they were able to say that this sliver of

this knowledge inside of this open source data set, we can

now talk to our downstream clients to say, no,

we can provide this level of confidence

with this level of information. And you put your level on

top of it, and you build some prompt engineering on top of that,

and then all of a sudden, you're getting the answers you're looking

for. Is that Sanitized data

that is now verified pushed back to hugging pace for. Other

people to well, because we're

investing so much money at this exact moment in time. Now,

that is going to be one of our selling points, is that we can give

you the core data. We can give you the data

set that we have built. Our model, and, of course, the model that we're going

to be offering to you through the Watson X platform will be so

large and so processor intensive, we need to run

it on our Mean. What does IBM have? It's literally business

machines, right? So we have a lot of compute power to do this stuff. So

we can run that model, but we can give you the actual data set and

we can say with legal penalties that this is the

data set that builds this model. So you can actually push

this out to and put your level of information on top of it to get

the information you're looking for. Okay.

I want to make sure let's take

all the things we covered, right? What's next? We've got clean, trusted data.

People can come along and say, okay, I'm going to use this for my organization

because I have this level of trust right now. I'd like to understand a real

use case that any developer listening to this episode would be like, yeah, that

sounds really sweet. Right. And I'm wondering,

could we take Kubernetes events? Could we take metric servers? Could

we push this all into Watson X? Can we derive

insights and predictability into our workloads on a Kubernetes

cluster as an example? Right. Is that something you're seeing people do?

Well, the answer is

yes, with a lot of Asterisks behind

it.

Yeah. Sorry. I'm a senior engineer. It depends

as much as the conversation we had around Watson X is, the

best part about of this whole narrative is that I use this

term in a lot of conversations I have, but it is valid in this

one. We want to be the Red Solo Cups of AI.

If you don't know what Red Solo Cup is, watch any

us. College movie, right? The beer pong cups,

right? That's correct.

Yes, exactly. Perfect. I'm not in the US. But that's all I know them as.

That's it. Yeah, but Solo makes an insane

amount of money on those things because they're everywhere. Right? They're just the way

you do that stuff. IBM wants to be

that of AI. We do not want you to interface directly

with Watson X. We do not

want to be B to C. We want to be B to

B. We want to give you an API with a trusted environment

to be able to work off of that. Now, the reason why I'm saying this

is because the developers that are listening to

your podcast right now, what I am offering to you is

a simple, non crazy Rest

API with Watson X that you can just literally

use. Use requests from Python to do a simple

post to the backend with a certain API

Key and a couple of requests of which model you want to push it through.

It's a really simple yeah,

JSON, and then it comes back with what

you want. So you do all the heavy lifting inside of Watson X,

but for your application, you can literally just leverage it a

little bit higher. Right. You just add one little request, and it comes back with

a nice little blob of information. So the practicality of it

is, again, it depends, right. But the

idea is we're trying to build the railroad for you here so you can

get the information you're looking for and be able to pull intelligently

back. Did that answer your question? It

did, yes. Thank you. I was going to say, so basically what you're trying to

do is you're trying to say, OK, see all these booths at KubeCon?

Imagine a number of these companies actually running on top of what's

next underneath, but you just don't know it yet. You as a consumer

wandering around, okay.

We'Re building phone lines, building the railroad, whatever you want to call it, whatever

major infrastructure change you're thinking of. In essence, we're trying to do that

for AI. You're trying to be Bell Labs is basically

what you're telling me. You're trying to be the old school Bell Labs that's building

out the original stuff that eventually everybody builds on

top of. Yep. And then on top of that, like, I

haven't even mentioned quantum inside of this space. Right. There's a

spur that goes into that ecosystem. Buzzwords. Don't just throw

buzzwords, JJ. I have a bunch of

PhDs, all they do every PhD physicist, all day, every

day, all they do is look at this weird ass computer

that's going to take all our lives or something. Yeah, exactly. That

makes sense. I guess my question always comes down

to there is a people problem under this to me, right under

AI in general, no matter where it ends up, if it gets

integrated into the cloud native ecosystem, or if it stays in the AI

ecosystem, I guess for lack of better term,

but

we can get the AI to start saying, here's the citations. We can get people

to try to verify everything, but we have that trust, but

verify. But how many people sit there and actually look at the citations?

Right. That always was a thing in science, I remember, was

people don't always check the citations. You have to learn to be very good about

checking those. It doesn't come to you naturally most of the time.

So how do we like, if I think about, let's say

that some company decides, okay, I'm going to build

a monitoring tool that goes through all of my live metrics

and analyzes everything using AI and comes out with an

idea of, okay, this system probably is going to fail, has like

a 20% chance of failing in the next 24 hours.

Right. Let's say that's an eventual thing because that's an

evaluation a person might do, but it gives you all the citations.

But who's going to go back and look at their logs to verify it

right now? Right. If I'm told like, oh, it works,

my reaction is, okay, it works. Right. So

how do you deal with that people problem when it comes to this AI question

of, well, we do have to verify it somewhere. Otherwise we

get pages that wake us up at 03:00 a.m. In the morning

for nothing, because nothing actually went wrong, because the AI

got it wrong, because they analyzed some other incident from somebody

else that just happened to have a correlation here or something, right?

How do we get there? I don't know if that makes any. Sense, but

how do we fix the chicken riddle problem? Can I try and

broaden that question? Because I think you're both thinking something very similar,

right? And I don't know if I'm trying to get there. Yeah, David, you might

be able to say this better than I can, so go for it. I don't

think so, but I had a question and then you asked something really similar and

I'm like, oh, if we just expect so let's try got all

we've got a world of AIS. Every developer is out there talking to a different

AI. I'm just going to call them singularities and AIS. Right, I know there's

deeper whatever now. We're all asking these questions,

we're all getting answers. And we mentioned licensing, we mentioned copyright.

Derivative works are obviously a huge challenge when it comes to people

using these answers to then put something out into the world.

So there's this ethical dilemma as well, which I think ties

into what Laura was asking is that if ten people go and

ask AI how to write a good song or a catchy song or a

number one hit, and then they all go start to use this, that's

ten different AIS that then somehow need to be answered. The question

of backtrack. Do we need

another AI to answer the question of was this written by an AI? Do these

AI companies need to work together to provide a transparency log to inputs

and outputs to prove that something was an artifact from

their algorithm? What's

the future look like? This is clearly a tough question or a tough

predicament. So how does IBM tackle that? How does what's Next tackle that?

Are there conversations with other companies? This was

actually a wonderful working session

at Fosse. We had this whole and I can

link to the Etherpad that captured all

the notes for this. And it was basically the

open source. If you don't know what Fosse is, it's what OSCON used

to be. But Fosse has broken off from it's the same

group of people, but not under the O'Reilly banner.

It's under the software conservancy. They're the ones who go after

the GPL people, right? They have the GPL lawyers

and they are an interesting breed, let's just put it that

way. Anyway,

the interesting conversation happened was, how can

you verify and say that this data

is not stolen? That was what it boiled down to, which is, I

think, kind of where you're going there. And

it always went back to the

this end entity, this Tarball. Sure, let's call it a

Tarball, make sure that this Tarball, which most

likely is a binary, isn't stolen.

It always went back to the data. It always kept going back to, if

I can prove to you that this Tarball came. Out of

this data blob through the model that I've

created and this data is verifiable. That

is the only way that you can backtrack through. Problem

is, models don't have like a shaw,

right? They don't have some way to say that this was the model that I

used to do off because the technology just doesn't exist, right? And

as much as we want to add all that stuff onto this stuff to be

able to say that, yes, this exists, the

ecosystem is already so large and has moved

forward so rapidly ahead of us, where you can get

an older version of Chat GPT on Hugging Face. You didn't

know they've open sourced those models. The models, not the

data, the models onto Hugging Face. So you can play with Chat GPT on your

local laptop. They're shit, but they do exist.

The challenge is we have no answer for that in the space. And the

way that IBM was answering it is through

doing the pile cleaning, being able to show you the

models and with legal penalties, with literally

pen to paper to this is we can show you exactly what's going

on. But Chat GPT, Microsoft, I can

tell you they will never do that. Right? As

much as we want to say that when

you go into the disruptors, I'm just using that

as a term to cover the non,

I say this with love the normies when they think about Chat

GPT, right? Those are the

disruptors, the ones that are going to be using it to write the paper for

their history class or whatever, right?

The models and the data that exists in that space,

the companies behind it, like OpenAI will never give us

those data sets. They will never do that. And then with Microsoft

investing their time and effort with Copilot,

right? That's one I kind of just skipped over, but I fall in the same

space as Chat GPT. As much as they

claim that they didn't take code from GitHub,

as much as they claim you can have only

Copilot only look in your we're computer

professionals, we know that's never true, right?

And as soon as you get that data slurped into the model, you

have no way to pull that data out. People forget that

models are. There'S no

reverting. Once you've trained something, there's no way to revert it

and pull it out. Not easily.

You could destroy the model and recreate the model with removing the data,

but then again, if that model is already out, just again, it's a compiler, you've

got to think of it as a compiler and then all of a sudden, a

lot more things start making sense. So Microsoft will

never give us a legal affidavit saying that, no, I did not

take any private repos from GitHub and

no, I looked through all of

GitHub looking for all the license files to make sure the Attribution is

correct on all of the Open source projects. I did that

alone is a Herculean effort. Did you get

trained off of this code that somebody just put up on GitHub? And there's no

default license, legally speaking, software

conservancy couldn't represent them in court. Going after

Microsoft because of that, right? And again, it goes back to what we

were starting at the very beginning of this conversation with Is.

We have no visibility into this space because the technology

moves so quickly without checks and balances that we are now at a

point where, okay, bad

analogy. And it just kind of hit me right now. Stick with me for a

second. You know, I'm the queen of bad analogies, so go for it.

In essence, we've created a bunch of

printing presses, right? All of a sudden,

we created printing presses all over the world that you can create,

that you don't have to organize anymore, that can just start

printing out information for you. And now what's stopping

you from selling those books? Right? Because there's no

validation that as long as you got that initial printing press with

the plates in it to give you the books to

shove out, that is what AI has done. It's given the ability to send

out that information very quickly, at least when we had the Internet, when it

first hit and people were worried about pirated books and stuff like

that, the ecosystem created

blobs of ways of secure pathways to getting

these things right and validated the itunes of

the world, if you will. But here,

that horse is already out of the barn and already to the next

town, right? We've got a lot of catching up to

do. And the only way and problem also is that

this is right. Like, this is not just

our friends in China. They could create LLMs that do all

the that create patents for them. And us.

Law means nothing. Right over there. They have their

own set of laws and their own ways to doing technology, and they have

a lot of computing power. Over

just I'm not trying to be doom and gloom. I'm just trying

to express this to our audience that we're talking to here. Saying

that as much as you think, hey, the joke of,

hey, chat GPT, give me an application. And it gives you

an application in five minutes. It does. Blah. You're going to be spending 24

hours debugging what the hell that application does because you can't trust

it. And there's this whole ecosystem around that that people

don't recognize that it actually spurs out to a lot of other stuff. Anyway,

sorry I got on a roll there. It's okay.

All right, so the TLDR is we're all doomed. It's all fucked. Go

hug your loved ones. Hugging face. Just turn off

the computer. Yeah, hugging face. Hugging the face. Hugging

face. Turn it off. And the next podcast will be coming to you.

Generated by AI. Our faces will be moving,

but we will not be the ones setting

I guess we're at the end of, like, there's a ton more to dig into

and who, uh, if there's more you want to hear on

this topic, by the way, there is a discord that you can join.

It's called Raw Code Academy, and there's a channel specifically

for cloud native compass, and I'm calling it out right now because I have it

open in another tab. But if you want to ask more

questions, maybe we can do another episode on AI someday

in the future. You can see. But yeah,

let me throw out a positive thing, right?

Or positive. Either one.

Sorry.

For me, right? I'm not in the ML space. I'm not in the AI space.

This was all new to me as Chat GPT and

OpenAI came out and Google Barred and all that sort of stuff. To

me, those were the only options. But I think we're in a really fortunate position

now. But there are other options. There's a lot of movement, it's a lot

of not volatility, but there's new

ideas coming all the time. And there's a lot more open source happening, too, and

there's a lot more trusted execution environments like we're hearing about Bozon X.

I think there's a lot of positive things going to come from AI, even though

it's easy to point out the scary bits, the negative bits.

Right. But I'm still extremely hopeful based on everything that

I've seen in the past and I've heard today from JJ. That is going to

have a net positive impact on my life and hopefully other people's

lives. I'm excited for the people working on this.

Okay? I'm excited. And at the same time,

I have more history in ML and

things like that from Python, but also from science. Just

thinking through that to me, I'll be honest, all of this is stats

all the way down and stats and I have a hate, hate relationship for the

rest of my life. Yeah, I just echo

and I'm just like doing my homework. Stop it. Scan lies and statistics. I mean,

come on. That's exactly how it works. I think Mark Two is a

little fiesta in that sense anyway. But who

knows? Maybe we'll get really lucky and it works out. But

JJ, is there any last thoughts, comments,

whatever? Because we're already longer than we normally are, but this is a really

interesting conversation, and maybe you have any last things,

last plugs, last whatever. Where can we find you online? All

that fun stuff? Yeah, well, first of all, I'm

pretty easy to find online, JJ, asgar most

places. If you are interested in Watson X, I do need

to plug the URL. IBM biz

dev Watson X The dash is the actual

dash. Not D-A-S-H but the actual Dash

Dev. Watson X. IBM is.

I do want to acknowledge that it is hard.

You think Kubernetes is hard? You think our

cloud native ecosystem is hard, and it is when you

start playing in the AI space,

be prepared to be confused,

question your ethics and morality, and

never ask what a developer advocate is, because I did

once, and it told me I was, in

essence, a CIA agent killing people. That was a little weird.

What? Okay, yeah, there's a reason I have.

Not created a Chat GPT account or any

AI. This was just an open source LLM. It was even better. It was just

like some generic open source LLM that basically described developer

advocates going sent out by Obama to kill

Russian entities or something like that. It was really weird.

It was really weird. For more exciting life than I

realized. On that note,

thanks for coming out, JJ. I hope it was fun. I hope you all

enjoyed David last thoughts. I know you're

lagging all of a sudden. Yeah.

I guess that's the answer. AI.

No, it's probably good. But on that note, thanks, y'all, for listening.

Thanks for joining us. If you want to keep up with us, consider subscribing

to the podcast on your favorite podcasting app, or even go to

Cloudnativecompass FM. And if you want us to talk with

someone specific or cover a specific topic, reach out to

us on any social media platform. Until next time, when

exploring the cloud native landscape, on three, on

3123. Don't

forget your compass. Forget your compass.

Bye.