#275 Did Gen AI Kill NLP? with Meri Nova, Technical Founder at Break into Data

Hi, I'm Maggie, VP of Curriculum at datacamp. And I know firsthand how overwhelming it can be to keep up with the rapid changes in data and AI. But staying ahead doesn't have to be hard. That's why our curriculum team has curated the best learning content to help you and your team stay ahead, covering everything from data and AI literacy for busy executives, to cutting edge generative AI for developers, and everything in between. Whether you're upskilling yourself or your team, we make learning practical, engaging and flexible. It just works. Power your data and AI transformation journey on datacamp.com.

I feel like there's a lot of opportunity when it comes to AI agents and AGI in general. Just because now that we understood how to communicate with computers with English language, which is super exciting, it can do things for us just because the things that we need to manage are in English as well. And before we didn't have the capacity for the computer to navigate these spaces. So I think this is very exciting just to see how the field is evolving.

Welcome to Data Framed. This is Richie. We got two topics today. So firstly, with all the hype around large language models, the previous generation of text analysis techniques known as NASA natural language processing tend to get overlooked. So I got to wondering about whether they're still relevant anymore. So are these things obsolete or are they a complementary set of tools? And secondly, I have an ongoing quest to figure out the best way to create generative AI applications. And it's been a while since we got into the weeds about which technologies and skills are important. Luckily, I have a guest who's an expert in both natural language processing and and AI application development. Mary Nova is an AI engineer and the founder of Break Into Data, a data and AI careers community. Her data science career encompassed everything from marketing analytics to robot computer vision. So she's got a very holistic view of the space. And on top of this, she's a Data Camp instructor, having created the Retrieval Augmented Generation with LangChain course. So let's hear what Mary has to say and find out about NLP and AI applications. Hi Mary, thank you for joining me on the show.

Hi there. Thank you for having me.

So, just to begin with, can you tell me what is natural language processing?

Sure. So natural language processing is one of the fields in AI that solely focuses on helping and enabling computers understand, interpret, process and even generate these days, human language. Pretty broad.

Do you want to tell me like some ideas of things that you can do with natural language processing or with text data in general?

You can Parse text, you can understand the semantic meaning behind it, you can even generate these days, as I said. So there are many use cases that NLP has. It's a broad topic.

And so in a business context, how might you make use of natural language processing?

I think the first thing that comes to my mind is having chatbots on your website that answers customers questions. And also big one is the content moderation. In things like Discord or different online communities, you can flag harmful content and you can also process documents and store them and retrieve information from them.

So I like the idea of just chatbots and processing documents like two very common businesses cases. It seems like these things have been around for quite a while now. I mean, we've had chatbots for at least a decade. So how has the advent of powerful generative AI changed the field?

That's a big question, I think because nowadays we are living through it and every day we see these new models coming up, especially within LLMs. And not that many people realize this, but I feel like this is one of the most exciting times in the history of AI, just because we have seen so much of transformation in the field and not only in NLP specifically, but in every other field, which makes it even more exciting. But generative AI specifically made us finally able to create large amounts of text data, which we couldn't before with regular machine learning and NLP specifically models. Because before it used to be only about parsing, understanding or just classifying a piece of text. And these days you can be a lot more creative because nowadays you can generate lots of data, which is super exciting.

Okay, yeah. So I think certainly like classifying text is fairly standard use case, it's been around a long time, but now having these sort of more creative conversations, it's going to improve the quality of your chatbots and things like that. So since you've got all these sort of wealth of like traditional NLP techniques and then you've got the new generative techniques, when might you want to use one or the other? Like when do you actually need these new powerful tools?

Yeah, this is a great question because I feel like these days everyone is just obsessed with LLMs and they want to patch it on every single business problem that you have. But I feel like it's generally a very wrong approach because these models are quite expensive and if you do not have a justified business problem that you want to tackle, I think you need to still stick to the traditional models which can help you with just clear and simple tasks where you can see patterns and like for instance, if you take spam detection in the emails, you don't have to use LLMs to say, hey, this is spam, or not, when you only have to say yes or no, basically. So I feel like people are just jumping too fast on the LLMs when there's so many great options that you should be using beforehand.

Okay, yeah, certainly I can see how just trying to use an LLM for a spam filter, that might be a bit overkill. So do you have a heuristic for when you might want to choose one technique or the other?

I generally try to stick to approach when if I need something creative, which is interesting, and I think it's controversial because we originally wanted AI to take on the mundane tasks, but nowadays we see a lot of it just involving creative tasks like generating articles. And just actually yesterday I saw Google's app that's called NotebookLM, and they generate podcasts like these based on the text. And I feel like it's very creative. But at the same time, many people are sad that we are basically giving all these models all the fun. But this is the heuristic. So whenever you have, let's say, very simple task with clear patterns like classification or detection, then you might want to stick to traditional models.

Okay, yeah. So that podcast one is particularly interesting. I have had to play around with Notebook LLM, and it seems to be a recurring theme on this podcast that guests come on and tell me that I'm about to be replaced. But hey, I have to say, you know, I think my job's kind of secure. Sometimes I stutter, sometimes I ask a stupid question, and that way, you know, it's like a proper human artisan product.

Yeah.

Not just AI perfection. So if you need creativity, then that's the case when you need to use more generative techniques, something a bit more powerful. So one of the grumbles I keep hearing is that actually once you start putting things in production, generative AI gets quite expensive. So does cost factor into your consideration for, like, what tools or techniques you want to use for nlp?

It's interesting because if you want to have your own custom LLM built, it would probably cost you around couple million dollars to say the least. And that's just training part. But when it comes to inferencing, it's another whole cost that you need to cover. So if you have novel ideas that you want to tackle and you feel like that can justify your business model, then sure, go ahead and build your own model. But many people cannot afford that. And again, if you're trying to build a feature that simple models can tackle, then I don't think the cost can justify itself. So yeah, I think it depends on the use case.

Okay, so in general you probably want to start with the cheapest. Actually I'm not sure whether it's the right round. You start with the cheapest tool and then see if it works or do you start with the tool that's going to give you the solution fastest and then see how expensive it is? Is there an order to which you would pick things?

I think it depends not on the cost of the tool itself, but rather how much does running that specific approach would cost you because running again the LLM would mean a lot more computational load and also a lot of data that you would want to store for your pre training and fine tuning purposes. But with simple models, like even not just simple, but like even previous neural networks that we worked with like bert, they just differ in the order of thousands of magnitude in terms of the cost. And yeah, I think it's worth having those first.

Related to this, I suppose how well the model performs is going to be an important decision. So how do you go about evaluating the performance of. I guess let's start with the traditional NLP models. What constitutes success? Is there an accuracy measure or what would you say constitutes good performance?

I think these days people focus a lot more on evaluating the LLM systems, which is part of NLP of course, but they focus a lot more on evaluation these days just because these are non deterministic systems that we have never dealt with before, especially in the production environment. And it can cause all sorts of failures, including security related ones too. Just yesterday I watched a video where a guy basically went on live and tried to have a simple SQL like injection attack, but this time it was through the chatbot. So what he did was he just typed in the question, trying to get the schema of the database of that company. So his end goal was to get the revenue for that month I believe. And LLM basically gave out all the answers to him. Even though there were security measures, basic security measures that had to do with lms, but still we're trying to figure out how to make them more not only deterministic but also safe to use. And I think it's still an open ended question. And there are many benchmarks and evaluation modules that different companies offer. For instance LangChain, since the course that I've been making with Data Campus with LangChain, they have their own frameworks that anyone can use on Langsmith. And there are other frameworks as well, of course, which has to do with more like RAG systems. I think the one that I was teaching in the course is from Ragas framework and it has, I believe there are four different metrics. The main ones which had to do with faithfulness and precision and recall, they sort of are relevant to the traditional metrics, but of course they have to take into consideration of the stochastic behavior of the LLMs.

Okay, yeah, so that seems like a very interesting thing. And maybe we'll get back to Lang, Jane and Langsmith and things like that in a moment. But you mentioned the idea that generative AI, these LLMs are probabilistic, so you're going to get a different answer every time. How does that affect how you even go about like saying, well, does this work or not? How do you measure the performance when it changes every time?

I think there's also benchmarks for LLMs performance without having to look at the task specific metrics. So definitely there is. On faithfulness and just a number of hallucinations that the LLM can make, there are benchmarks that evaluate purely the LLM's performance.

Okay, all right. So there are some tools out there. It might be slightly more complicated than just the sort of traditional thing where you've got a single number as an answer. So you mentioned some of the tools you've been working with when you were teaching how to work with LLMs in your course. So do you want to talk me through like what's the current tech stack for working with LLMs then what are the different tools you use?

I think everyone has their own tech stack when it comes to LLMs, just because also the number of models, the open source models that we have on Hugging Face is around hundreds and hundreds of thousands of them. And it becomes a task of just like understanding which one that works best for your use case. And everyone has their own way of deploying those models into production. But again it depends on the database that you're using. And in our case it's vector store that you're choosing. There are many third party vector stores that you can use and that's number one. And also the retrieval systems that you're putting in place. And in the course we're going over sparse and dense embeddings that dictate the type of retrieval that you'll be using and the evaluation frameworks, of course. And where would you like to host your model to? If not Hugging Face, then where and how you would like to monitor your Models and where your logs will go and so on and so forth. But my favorite ones, I actually, I think made a post a couple months ago about my favorite tech stack. But I'm a big fan of what Weights and Biases does. I think they have a great environment and great support. Other than that, there are many options, like on Hugging Face. Hugging Face is one of the most available and the just popular ways to deploy your models.

Okay, cool. So we've got some sort of vector store to store all your data for the fact retrieval. And then you mentioned you need somewhere to host your model. So something like Hugging Face. You mentioned weights and bias as well, which I presume it's also like a model tracking platform. And then there was some sort of evaluation framework as well, so lots to go there. Maybe we'll start with like the vector store. So do you want to sell a bit more about what are these vexistore stores and how do they fit into the whole AI system?

To give you context, the GPTG models that we have I believe were trained on 40 something terabytes of text data, which is quite a lot. And you need a way to store that unstructured data in one place and be able to retrieve them as well. So there are great vector stores that originated in San Francisco, which is interesting. I met a couple of the founders and founding engineers of Chroma db, one of the conferences in San Francisco. And it felt like at one point everyone is surging to like open and start a vector database just because the demand for it is huge. So vector database is basically data storage for all that text data that you have. And it allows you to create these embeddings from text, which is a hierarchy. Embeddings are the highly numerical values in a vector. So like one token, let's say it's a one vector and it can have hundreds and hundreds of dimensions and you need to be able to store them in one place. And also you can have a way to understand the relationship and the semantics underneath this text. So it's not only just storing, it also stores it in a way where it understands that let's say gender is a thing or the transportation is a thing and car is related to transportation and so on and so forth. That's the gist of it.

Okay, so the vector storage is a place to store chunks of text and then you've got an embedding model that's going to tell you what the meaning of the text is. You can find similar text. I guess the idea.

Exactly.

Okay, Just continuing on the subject, do you want to talk us through like some of the use cases for this? Like when do you actually care about having a vector store as well as having the LLM?

Pretty much all the time. I mean, so vector stores are, let's say if you're building a system that has your own custom built LLM. So in order for you to have your own model, you need to have a vector store so that you can store all the embeddings that you have created and be able to retrieve from them. So in our case, when we created the rag, we used vector sort to basically transform the document corpus that you have into the embeddings and store them in the vector store so that next time a customer, let's say visits your website and asks a question, you can convert their query into embeddings and then use a similarity search so that you can find similar words or documents that have to do with this query so that you can respond to the user's question. And that's the case with rag. At least you need a vector store, but in other cases you need it to store your training data and fine tuning data as well. But if you are just using a third party API, you definitely do not need a vector store. You just need to have good prompts and work with them.

Okay, so really it's any kind of use case where you have to have some kind of factor retrieval. I guess the big use case is about reducing hallucinations, right? So it's like if you want to work with a document or you want to have a chatbot or whatever, then it's going to involve this retrieval augmented generation at some point.

Yes. Not only reducing the hallucinations, but also having a way to integrate your own proprietary data into your LLM system so that you do not need a human to be able to answer customers questions.

I like that. Yeah. So avoiding humans, I guess it's a bit of a double edged sword there. It's like if that's your job questions, then being replaced by the AI is kind of hard. But also if you're just answering the same questions over and over again, then maybe better done by a bot rather than making you go crazy answering the same questions over and over. So actually I think this leads nicely into talking about the organizational side of like working with text. So at the point where you start talking about, well, maybe AI is replacing humans in some place, that sort of suggests that some of your processes are going to change. So once you start working with these newer generative AI tools. If you are an AI engineer or a natural language processing scientist, then talk me through how your workflow is going to change.

Now. I think the title of AI Engineer actually became a lot more popular since the advent of LLMs. Just because before it used to be ML engineer or NLP engineer or computer Vision Engineer, but these days I guess when people say I Engineer, it's very generic. Actually I think I would put even ML Engineer title with underneath the AI Engineer. There's a huge debate on this, that's why I'm quite specific about this. But the workflow, I think it depends again on the domain and how are you implementing LLMs. But if you've never worked with LLMs and you would like to start working with them, it depends on choosing the type of path that you're taking. For instance, again, training and having and hosting your own model is a completely different workflow than let's say finding and searching for an open source model and fine tuning it for your specific tasks that you wanted to perform. And the third one is just again finding the cheapest third party API and integrating it into your system. Those are three different things and I believe the skillset does also depend on that because the first one demands a lot more of the scientific understanding of deep learning concepts and how to process large amounts of data. And those other two, I think more related to engineering side and deployment side and system design side as well as just having great prompts. So it depends on the approach you take.

Okay, yeah, so that's interesting that although AI Engineer is the very kind of, it's becoming a very popular job title, there's actually lots of different things involved in that. So messing about with Pytorch to create your own models or fine tune models, that's a very different proposition to just calling APIs. And I say just calling, I told you to be that as a, as a job skill. So. But if you're calling APIs and pulling in or making use of other models, then that's again a different skill. So in general you mentioned that AI Engineer is kind of, or at least part of it is the same thing as a more traditional machine learning engineer. How do you see all these roles changing at the, the moment?

I think that's the million dollar question. Just because I write for aspiring AI engineers and machine learning engineers and that's one of the top questions they ask. It's what kind of skills that we need to prepare and especially those who are graduating from master's or bachelor's degree and are trying to get their first jobs. I think a lot of it has to do with the strategy that you choose. But the one thing that does not change is if you have a specific domain expertise and then sort of adapting your skills to that domain, that would definitely give you a competitive edge in any scenario. But if you are looking at the skills as an engineer themselves, I would say just understanding these concepts are super important because if you're trying to deploy again, non deterministic systems and you do not know how they behave and how are they created and what are their dependencies and the outputs look like, then I think it will be really hard for you to even understand the, the opportunities that it has. And yeah, so I think it's just about staying open minded and learning every single day. Just because there are so many tools that are coming out. And for my audience, I usually just tell them to stick to the fundamentals, which is in our case especially these days for deep learning is linear algebra and also of course statistics and probability. And once you have these fundamentals in check, it'll be very easy for you to adapt to any other tool because now you know what are they comprised of and you can even come up with your own tools, which is just a great place to be in in any case.

That's interesting that you recommend learning a lot of the fundamentals then. So linear algebra, statistics, things like that. I think a lot of people that jump straight into, well, I want to do something with a tool and kind of skip over some of the fundamentals. So it's interesting that you are like advocating for learning these sort of lower level things. Are there any particular techniques within linear algebra or statistics that you think are particularly important for people interested in machine learning or AI?

Yeah, I actually had this debate online with another person, another creator who disagreed with me and sort of had this argument and his opinion was that you need to build and you do not really need to understand these underlying concepts. And I agree you can build things without understanding them, especially these days. But my approach is mainly on just getting on back to the first principles thinking just because I think that will give you a lot more freedom in your creative approach as an engineer as well. And I believe in our world of like following the trends and just especially, especially these days when you have these transformers and large language models that can do almost like everything. I feel like people forget that these architectures have also been created quite recently. And it does not mean that it's the only path forward. In fact, there are many architectures that have been invented alongside neural networks in the past, but have been forgotten. And I feel like if there was a lot more creativity when it comes to building architectures and building models, we could even arrive to AGI, which is also a hot topic these days in Silicon Valley, a lot faster or even cheaper and we can even maybe have more control over these models. And yeah, I think I mostly I'm excited about these things, but when it comes to statistics and linear algebra, I would say have an intuitive understanding of how matrix multiplication work and how vector transformations work and how optimizations work, as well as calculus, understanding derivatives and basically how the rate of change happens in these models and in statistics, that's causal statistics. But statistics is mainly for traditional machine learning. However, with neural networks it's mainly linear algebra and people think it's very complicated, but I believe it's just the notation that scares many people away. But when you look underneath the notations, it's simply just multiplying A with B and adding in Y and just doing it million times over and over. And I think that's it.

I love that idea. Well, yeah, linear algebraic is multiplying, adding numbers at its core. Dead easy really. Yeah. So yeah, I can certainly see how I'm saying that. Actually everything with a neural network is basically just matrices underneath and some optimization routines. So having a basic understanding of those is going to be quite helpful. So you mentioned that people aren't very creative in their architectures and some of the sort of traditional machine learning techniques are getting ignored or forgotten about. What do you think people are missing out on? Like what are the most undervalued machine learning techniques at the moment then?

So I have a co founder and his name is Kostya and we are both building Break Into Data, which is our community for machine learning engineers and data professionals in general. And when I met him for the first time, he influenced a lot of my thinking and a lot of my just thinking about machine learning in general. The first time I met him he was telling me a lot about Fourier transforms and how you can process audio without text and how you can combine and mix these algorithms and formulas together and just come up with a completely different approach. And I really liked his way of thinking because like before meeting him and just understanding his way of thinking, it was mostly just learning pre existing frameworks and just strictly following those to get results. And I finally understood that you do not have to be locked in these conventions to solve even the same problems. For me, we started working and just researching about symbolic AI and how you can integrate Symbolic AI with knowledge graphs and sort of create this entity that can understand things not in a way of statistics where you have large corpus of data, but rather have it behave just like a human brain does, which is just accumulating knowledge over time and having these understanding the relationship between things. And that's why knowledge graphs are there too. So I think there's just a lot of it comes from math these days. But even nowadays you can just use Python and nothing else but Python and start with just like simple algorithms. And the way he taught me to do this is just come up with the recommender system that just like links your relatives to one another and just understands the relationships between them and, and so on and so forth. So like having these like small challenges will make you creative and also will make you understand the practical implications and opportunities of what you can create.

Yeah, so lots of very cool stuff. I do like the idea of having was a recommended system for your relatives. It's like, oh, I don't recommend Auntie Nelly. Yeah, but that's really cool.

We have hundreds and hundreds of relatives and it's a lot of data to go through.

Big family, big data. Nice. Yeah, I do like the idea of having just a simple project that's just personal to you though, just to practice things on. And that just seemed like a great idea for working with knowledge graphs actually. But yeah, also interesting that you mentioned Fourier transforms. I think it's like a physicist's favorite and I guess anyone involved in like music recording, they're going to be very familiar with Fourier transforms. But yeah, that is an interesting idea that we've taken over, like just using generative AI for working with audio. But actually there's a ton of techniques that are around for decades. So it also seems like a lot of the tools are making it easier to work with AI and both data in general. So is that changing who can build things or who can make use of this? Like, is there. Do you think the population of like who is working with AI or data is changing?

Yes. I was also thinking about LangChain a lot and when I was thinking about what kind of course to create with datacamp, I wanted to do it with react, just because back then it was very popular and I mean still is, but LangChain specifically, especially in the more experienced crowd of machine learning engineers and just Python developers in general, they do not like it. And it's funny to see because whenever I tell them I'm making a course and they're like, what are you making a course on? I'M like LangChain. But he's like, why out of all the things you choose LangChain? But I think there is a place for LangChain to exist and I think people do not appreciate it enough, especially for those who do not have engineering background. And LangChain itself sort of brought to the field of what's possible with LLMs and how to digest LLMs better. And people don't appreciate this and they think their documentation is terrible and things like that, which might be true because they're just changing a lot of their versions. So. But other than that, I think they are definitely leaders in implementing LLMs and showing us the way. Sort of like paving the way to the production environment with LLMs. And that's interesting because people that do not have experience can greatly benefit from exploring LangChain's methods and different modules they have. But people that do have experience, and especially engineering experience, they can tinker around even further and have this flexibility of like coming up with anything that they want. Their own unique evaluator, let's say, or their own unique way of retrieving things or combining and having a hybrid retriever or things like that and just also being creative with the prompts. And yeah, I think that's just two different levels. And I definitely urge everyone to focus more on the engineering side so that they do not rely on libraries like LangChain. But LangChain is definitely a source of inspiration for many of the new tools that are coming now to the field.

Interesting. So I hadn't realized there was such controversy around LangChain. So you're saying it's a good beginner tool, but if you're an engineer and you're comfortable tinkering around with APIs, I guess directly, then maybe you don't need it. All right. And you mentioned there are some other new tools that have been inspired by LangChain. What are these other tools?

There's other retrieval based tools like Llama Index, for instance. They're also from San Francisco and I've been to one of their talks. They talk a lot about agentic AI and how they are making it decentralized and they're sort of coming up with their noble ways of implementing AI agents. So that's exciting. And I think there are a lot more that. For instance, what else? DSPY is also becoming very popular for prompt engineers because they're trying to make it like a programming, even though it's human language. But I like the way they come up with the systems and frameworks that help us implement LLMs. So there are many more and I haven't even explored that many, but these are come to my mind now.

So you also mentioned knowledge graphs as being an important component of any AI system. So you mentioned the idea of having like looking at the relationships between your relatives. Beyond this, can you talk me through why would you want a knowledge graph and how would it fit into your AI?

So in the course that we made with datacamp, our last chapter is on Graph rag. And when I started developing the course, I think about that time Microsoft released their Graph rag as well. And people sort of realized that graphs can make Rack systems a lot more efficient. And the way they do it is basically the retrieval system that we have with the Rack these days has to parse through lots of data to find the most relevant documents or text to put into the output. But graphs, what they do is they give you the higher level a relationship between the main entities that you have. And that significantly reduces your search space and computational load therefore and would also allow your outputs be more relevant to the document corpus in general. So graphs in general, they are considered to elevate the RAG systems and even though we do not see a lot of them in the production just yet, just because it's relatively new way of implementing rag. But I think there's a lot of opportunity there too because simply because it gives us a lot more understanding of the document corpus which is harder to get with simple retrieval systems.

So yeah, I think like the standard RAG approach, you're looking for things with cosine similarity or something. It's back to simple linear algebra to find what's the the best text. So having something more sophisticated might give you better results. So that sounds very cool. Is using all this sort of relationships between bits of text to like find what's the best text to include in your response. Have you seen these success stories with it yet? Is it too soon or are there any people like building cool things using this graph rag technique?

I especially for graph rag I haven't seen as much blogs from big tech or any startups yet. I've seen lots of tutorials on this. I feel like this is relatively new approach and people were kind of skeptical about this just because it's. It adds another layer of complexity when it comes to dealing with your database. And not that many people are ready to get to that. But other than that, outside of rag, Knowledge graphs have been popular since a long time now decades. And one of the popular implementations of knowledge Graph is Google also having I think they had a Couple hundred millions of nodes and facts stored in their database around just historical facts on musicians, writers and so on and so forth. But other than that, I haven't really seen any implementations in the production. But I'm excited. I feel like they will come out soon.

All right, so is it an open space for anyone wanting to be first to build something cool. So some good opportunities there, I guess if you want to build your own search engine as well.

All right.

Takeover would be the next Google. All right, so just to wrap up, what are you most excited about in the world of NLP and AI?

I am honestly excited. Since the beginning of my machine learning career, I've been excited about automation and NLP specifically. And I feel like there's a lot of opportunity when it comes to AI agents and AGI in general. Just because now that we understood how to communicate with computers with English language, which is super exciting, it can do things for us just because the things that we need to manage are in English as well. And before we didn't have the capacity for the computer to navigate these spaces. So I think this is very exciting just to see how the field is evolving, especially in San Francisco. And I go to lots of hackathons and they always come up with the novel ideas of how to automate your browser related tasks or have your own assistance. AI based assistants that manage everything for you, respond to your emails, schedule your calendar and make decisions even for you just based on the facts that they know about you and just also having it as a companion. I think it's very underestimated just because I am a huge advocate for CPTSD and ADHD and most of my time is just having this like my prefrontal cortex trying to understand what's the next priority and making the decision is really hard, especially if I do not have anyone to analyze the situation. So I just take a chatgpt and I'm like okay, here's the facts that I have right now. Help me digest this and make the best decision. And we just go through one by one and sometimes I'm just like wow, this is crazy. It simplifies my life and I know that I can use this tool anytime I want and is just wonderful. And I feel like people are still not using it enough. There are so many use cases that we have for this amazing technology that we are still discovering and I feel like this is a nice era for us to experiment and that's my favorite place to be. It's just the constant experimentation and finding things of how to use this technology to make our lives better.

That is actually a very cool use case. I like the idea of, yeah, ADHD is just having something to just help you make decisions and sort of take away having brain fog and just things go around in your head. You just got someone to chat to. It's like a more advanced rubber duck, I guess, someone to give you a response. Do you have any more use cases like that just for AI in day to day life?

Oh, interesting. I mean, I use AI a lot in terms of especially content, just because I'm a content creator. And I feel like before AI, if I was a con, I was not a content creator before AI, by the way, which I to this day I'm like, oh my gosh, how did these people come up with like ideas and how did they edit their text and things like that? But these days it just makes my workflow so much more enjoyable. And sometimes I can just like have this creative duo with, with AI where I tell a joke and then I ask it to tell a joke that's similar to this joke and then I just have this loop of like funny jokes and that's the way I create content, especially for memes. But yeah, I think it's a great mirror of your own imagination. And I am really grateful again to. To be alive during this technological advancements.

That's a good way to wrap up there. Really grateful to be alive in this amazing time. It truly is an amazing time. All right, thank you so much, Mary, for your time and your thoughts.

Thank you so much, Richie, for having me.