Jeremy Utley on Crafting Smarter Conversations with AI
Today, we’re thrilled to welcome a special guest, Jeremy Utley, an academic marvel from Stanford, whose work on AI and idea flows is altering the landscape of business and innovation. In this episode, titled “Jeremy Utley on Getting the Most out of LLMs”, we dive into Jeremy’s FIXIT approach for leveraging Large Language Models (LLMs) such as ChatGPT.
Jeremy will unpack the nuances of FIXIT, showing us the importance of providing context, iterative interaction, and team incubation while using AI. We’ll reminisce about how technology has evolved from cell phone minutes to AI, which is becoming as ubiquitous as smartphones once were.
Frank will voice concerns about the technical aspects, like token length, while agreeing with Jeremy’s method. We’ll examine why AI needs to be seen as a collaborative partner rather than a magical solution. Jeremy will shine a light on his book “IdeaFlow” and share his insights on the psychological barriers hindering the effective use of AI in practice.
Expect to hear anecdotal wisdom about the transformative impact of ChatGPT, the importance of prompt engineering, and the potential of AI to refine negotiation skills. Jeremy will even offer examples of how generative AI can offer fresh perspectives on personal and emotional decisions.
Don’t forget Frank’s experiments with creating custom GPTs, such as for our character Bailey. Our lively discussion promises to leave you with a wealth of knowledge on interacting with and extracting maximum value from AI.
For all this and much more, stay tuned in as we journey through the possibilities and realities of AI as a tool for amplifying human capacity.
And before we kick things off, a quick reminder to check out Audible for the best in audiobooks, and please take a moment to rate and review Data Driven to help us grow and bring you content you love.
Now, without further ado, let’s get data driven.
Show Notes
00:00 “Idea flows: the only business metric that matters.”
05:35 Striving for the best is essential.
06:46 Expert hesitations on using AI for knowledge.
11:27 Asking for help, ended up with an image.
14:41 Convince family to take job offer role-play.
16:08 Learning new skills and fostering imagination through technology.
19:54 Seek understanding from personal experiences and examples.
25:48 Keanu Reeves movie sparks philosophical wonder.
28:42 AI prompts emotional epiphanies for life decisions.
32:11 Accidental query on creating GPU prompts explanations.
36:08 Instructions for using voice mode during coaching.
39:50 Ease of use and utility in busy life.
43:18 Key to AI success: Team collaboration is essential.
47:07 Kids don’t care about data plans.
50:45 Released groundbreaking technology; implications for all industries.
53:18 Excited to buy internet access for chat.
54:54 Jeremy Utley wows with innovation and wisdom.
Transcript
Today on the data driven podcast, we have the privilege of hosting
Speaker:none other than Jeremy Utley. Now, Jeremy
Speaker:isn't just any guest. He's an academic marvel
Speaker:and entrepreneurial spirit rolled into 1. Hailing
Speaker:from the prestigious corridors of Stanford as an adjunct professor, he's
Speaker:the kind of chap who educates the future disruptors of Silicon
Speaker:Valley. He is here to tell us how to get the most out of
Speaker:generative AI. Now on to the show.
Speaker:Hello, and welcome back to Data Driven, the podcast where we explore the emergent fields
Speaker:of artificial intelligence, data engineering, and data science,
Speaker:and all the associated technologies. With me today is
Speaker:Jeremy Utley, who is a, adjunct
Speaker:professor, venture investor, and co author of the book,
Speaker:Idea Flow, The Only Business Metric That Matters. Welcome to the
Speaker:show, Jeremy. Thanks for having me. Hey, no problem.
Speaker:So Stanford. That's kind of a big
Speaker:deal. It's a it's a special place. Yeah. I'm
Speaker:just trying to not get found out. I'm sure it's, you know, similar to,
Speaker:the, the guy on Office Space. Right? At some point, there'll the clerical error
Speaker:will be revealed. You'll you'll know when they move you to the
Speaker:basement. Right? Exactly. Exactly. Yeah. But I've been teaching at
Speaker:Stanford since 2009, and I've been delighted to get to learn alongside some of
Speaker:the most incredible students in the world and and get to study some of those
Speaker:incredible innovators in the world. So, not just I may be a
Speaker:professor or an adjunct professor, but I really consider myself to be a front row
Speaker:student in in the classroom alongside my students. Very
Speaker:cool. Very cool. So, what
Speaker:what is the most important metric? I'll start right there.
Speaker:Well, the most important metric we call idea
Speaker:flows, the only business metric that matters. And the reason that we make that bold
Speaker:claim is because it's the only measure of your
Speaker:team's capacity to solve problems. And the the only
Speaker:constant in our day to day lives is problems. In in our businesses, I
Speaker:don't know, a single business that is facing a day without problems. And
Speaker:so if you think about problems as the constant, then your
Speaker:team's capacity to solve problems is really the most important thing
Speaker:that you should be measuring. And yet, nobody really even knows how to
Speaker:measure it. And so we talk about idea flow as the as the way to
Speaker:measure a team's capacity to solve problems.
Speaker:Interesting. Interesting. And is this is this changing now when we have the
Speaker:reality of AI assisted teams?
Speaker:Yeah. Yeah. Absolutely. That's it's a really insightful question. Yes.
Speaker:It does change or sorry. It has the
Speaker:potential to change. And yet, what our research suggests that we've
Speaker:conducted over the last year or so, is that sadly, it
Speaker:actually doesn't change in practice. In theory, it could change but in
Speaker:practice it often doesn't. What's interesting, so what
Speaker:what are the barriers to this? Right? Because I have some thoughts on this. I
Speaker:know that a number of companies have basically outright
Speaker:banned, use of AI tools
Speaker:with good intentions, right, because the privacy policies, etcetera, etcetera,
Speaker:but in reality, people are copying and pasting sensitive stuff anyway.
Speaker:So, it seems like banning something outright
Speaker:doesn't always work in a number of areas. But
Speaker:what what are the barriers? Right? Because it it it can, like
Speaker:you said, but in practice, what's what's what are the blockers?
Speaker:Ultimately, it's it's human psychology, really, is what what's,
Speaker:the challenge. It turns out that our expectations of the technology,
Speaker:are hamstringing our ability to make use of it. Because
Speaker:we're approaching the technology. Most teams that we studied
Speaker:approach the technology as an oracle. It's almost like a search
Speaker:box. It's gonna give them the best answer. Right?
Speaker:And that's the wrong way to approach the technology. It does feel somewhat
Speaker:magical when you type in, you know, an enigmatic query
Speaker:and get a seemingly intelligent response. I mean, that feels
Speaker:magical, but the teams that do that underperform. The teams
Speaker:that overperform are the teams that
Speaker:treat generative AI not as an oracle, but as a thought
Speaker:partner, as as a conversation partner, and iteratively
Speaker:work together with the AI to discover a better answer.
Speaker:And the irony of that is it's not very magical, actually. It feels
Speaker:like work. And yet, where teams that
Speaker:treat AI as a conversation partner arrive is
Speaker:light years better than teams that treat
Speaker:AI as an oracle perform.
Speaker:Interesting. So what are the what I think I know what you're
Speaker:getting at in terms of treating it like an oracle versus treating it like a
Speaker:conversation. Because I've seen that as I do more and more of this, I
Speaker:hate the term prompt engineering. I hate the strong word. I have mixed feelings about
Speaker:the term prompt engineering because there is no one single prompt to rule them
Speaker:all. Mhmm. At least that's been my experience where you kind of you kind
Speaker:of it's like a conversation, like, you're having. It's not a
Speaker:person I know. It's not a person I know. It's not a But it's but
Speaker:but it is a mindset, Frank. That's the thing. It's a mindset. And people
Speaker:don't come with the mindset of I want to have a conversation. People are lazy.
Speaker:Right? So so Herbert Simon, back in 1954,
Speaker:won the Nobel prize for what he deemed satisficing, which
Speaker:was the human tendency to settle for good enough. Right? And in most
Speaker:of our lives, it's fine. I need a good enough pair of jeans, I need
Speaker:a good enough cup of coffee, whatever it is. Right? But when we're trying to
Speaker:solve problems, good enough sometimes is is okay. But often, especially
Speaker:when it pertains to innovation, you don't just want the good enough thing. You want
Speaker:the best thing. And it's in that area where when we really
Speaker:want the best solution, that our tendency to settle for good enough
Speaker:really hurts us. Because what teams do is they put
Speaker:in a prompt and they get a pretty good answer and they go, woah,
Speaker:I I was prepared to take an hour working on this but we kind of
Speaker:got pretty good in 5 minutes. You guys want to go get coffee? And everybody
Speaker:just gives up because they got good enough. And so that's,
Speaker:you know, I I think it really is a mindset thing. Forget the word prompt
Speaker:engineering. It's all it's it's self engineering. It's human
Speaker:engineering. And one of the best things that a human being can
Speaker:do is say to the AI why they don't like
Speaker:the answer the AI gave. Right? So take your expertise.
Speaker:Here, this is something that anyone is listening can do right now. Take something
Speaker:that you know you're an expert on. So for example, I'm an expert
Speaker:on customer insights or or low resolution prototyping and
Speaker:experimentation. Right? So I might say to the AI, can you give me a
Speaker:step by step guide for how to conduct an experiment? K. If I
Speaker:did that, we can do it right now live if we wanted to. But if
Speaker:I do that, it's gonna give me like, you know, the average of the Internet.
Speaker:Right? And it's gonna draw from a bunch of stuff that may be good, may
Speaker:be bad. By the way, I'm an expert, so the chances of my knowledge surpass
Speaker:it are reasonable, you know, at least. But because it's gonna give me
Speaker:the average of the Internet, it's probably gonna find some corners that I don't know
Speaker:about and it's probably gonna say some stuff that I vehemently disagree with. Well, where
Speaker:most people give up and I think because they want AI to not
Speaker:be that good is they look at the response and they go, see.
Speaker:It didn't even know that you're supposed to test for desirability and not
Speaker:feasibility. Right? Whatever. And then they say, that's why AI is no
Speaker:good. Well, Human Engineering, not Prompt Engineering.
Speaker:Human Engineering is to say, okay, human, tell the AI
Speaker:what you disagree with and why you disagree with it,
Speaker:and ask the AI to regenerate an answer
Speaker:given the following considerations and put in your critique.
Speaker:Most people if they do that, just even that one thought exercise,
Speaker:will be blown away. Yeah. You get an order of magnitude better response.
Speaker:Absolutely. Right? Absolutely. Because you're kind of focusing the cone
Speaker:of, you know, inquiry with your own
Speaker:expertise. And what people want is they I mean, no one would
Speaker:ever if you think about, like, AI like an MBA intern. Right? No
Speaker:one gets an intern from Harvard Business School, gives them 2
Speaker:sentences of instruction and then at the end of the summer says, man, their workout
Speaker:was no good. I didn't interact with them at all. I didn't give them any
Speaker:guidance. But for crying out loud, what's
Speaker:Harvard doing these days? Right? No. Nobody gives a
Speaker:human being 2 sentences of input and then critiques how bad of a job they
Speaker:did, right? And yet we open chat gpt, we give
Speaker:2 sentences of input, if that by the way, and then we go, See, it's
Speaker:not very good, well, work with it. Garbage in garbage
Speaker:out. It's as old as possible. And the reason most people don't I think most
Speaker:people don't wanna work with it is because they don't want it to be any
Speaker:good. Yeah. I could see that. Totally.
Speaker:And the people who do want it to be good will be unlocked and
Speaker:unleashed. But it requires not prompt engineering, but
Speaker:human copilot engineering. I do like the
Speaker:fact that a lot of these tools that are coming out are being called copilots,
Speaker:right? Because I think it shifts the focus away from
Speaker:AI isn't going to do it all. AI is not
Speaker:probably gonna take your job, right? But it's just an
Speaker:assistant. Right? It's it's to help you out where you may
Speaker:want a little bit of boost. I also think that I think what you you
Speaker:described is good enough factor is I think people see
Speaker:large language models and they they assume it's a search box only
Speaker:better. Yes. Well, and part of our
Speaker:challenge, you know, I was talking with a with a psychologist, David
Speaker:McCraney, who wrote How Minds Change. He's a he's a journalist, an author,
Speaker:a podcaster. He's a he's the host of You Are Not So Smart, which is
Speaker:all, you know, obsessed with cognitive bias, which I love. Mhmm. I love
Speaker:that podcast. And one of the things that David and I were talking about yeah.
Speaker:I can't remember the the name for the cognitive bias, but when we see
Speaker:something that we think we understand, we just track into
Speaker:our kind of typical neuro pathways. Right? So we
Speaker:see a text box and we go, oh, I've seen one of these
Speaker:before. This is like that. And we so and this
Speaker:this being generative AI is not like that. That being
Speaker:search. Generative AI is not search. But because of the
Speaker:kind of the the UI, we
Speaker:approach it like search. We go, okay, I want the answer. Just give me a
Speaker:list of links that I'm gonna click through and decide on. And we don't
Speaker:interrogate Google, we don't critique Google or any search
Speaker:engine, right? We don't say why we want it
Speaker:or state our intention, right? But if you start to do
Speaker:some of these fundamental kind of human
Speaker:conversational tactics, if you start treating it more like a
Speaker:person than like a search box, you get
Speaker:exponentially better results. But you're right, even
Speaker:the UI itself predisposes us to treat the
Speaker:technology and to think about the technology in a particular way and
Speaker:that is actually holding us back. Interesting. I noticed
Speaker:this in a completely random thing. I was getting,
Speaker:I was using DALL E to generate images, This is before Chat GPG had it
Speaker:in there. And I wanted to make a painting that looked like a Rembrandt painted
Speaker:a portrait of a dachshund. I know this is the most ridiculous thing.
Speaker:Right? So I wrote the prompt, I said, you know, painting of a dachshund in
Speaker:style of Rembrandt, and it produced something. It was okay. Right? It was
Speaker:good. But I was like, I wonder what if I asked
Speaker:ChatCpt to help me with this prompt? So I went over. Now
Speaker:I could do it all in 1 window. But I said, like, hey. What would
Speaker:what would you write for a prompt? Like, what would do that? And it came
Speaker:back with, I mean, a paragraph to what you said, 2 sentences. This thing came
Speaker:back with a paragraph. I mean, stuff that only art historians and art,
Speaker:students would really appreciate. You know, this type of paint, this style of
Speaker:brush, like, just stuff that I remember from art history class, but, like, you
Speaker:know, I only took that class because I had to type thing, you know?
Speaker:But but then I I pasted that prompt in there, and, oh,
Speaker:okay. It's it's it's an image. It's art. It it it's somewhat subjective, but
Speaker:the the result was so much better. Like, it was just day
Speaker:and night, and That's true. That has changed the
Speaker:way I think about, dare I say, prompt engineering. Right? Like, because you can
Speaker:because I gave a talk on prompt engineering and, like, you know, the magic of
Speaker:it, and I was like, you can actually have the models help you build out
Speaker:prompts. Yes. Well, that's that's the thing that people don't understand
Speaker:is, you know, I mean, I I interviewed the other
Speaker:day on a I've got a podcast called Beyond the Prompt, which is all about
Speaker:AI in organizations. And we've interviewed a bunch of amazing people.
Speaker:You have co founder of Typeform, CEO of Section,
Speaker:CEO of Every, the head architect at Instacart, a bunch of
Speaker:interesting people. And one of the folks we interviewed last week is a
Speaker:documentary filmmaker named Juan Carlos. And Juan Carlos has made some
Speaker:amazing documentaries. And he said he's always wanted to build
Speaker:an Ios application, but he's never had a developer and he's always seen that as
Speaker:kind of prohibited. He can't do it. And then he said when ChatGPT came
Speaker:out, he had the thought, could ChatGPT teach me how to
Speaker:code? And he built an
Speaker:Ios app by treating ChattGPT like his computer
Speaker:science TA. And he would go to the TA and ask for
Speaker:instructions. He got Chad GPT to teach him
Speaker:how to build an Ios app. Nice. You would
Speaker:never imagine doing that with a search engine, right? No. You would find it on.
Speaker:You would find it on. But you would just, and anytime he got stuck, You'd
Speaker:come back to the TA. Right? And you get more. But your
Speaker:point about people's minds being open, I think they have to be
Speaker:hearing examples like this. He literally went to
Speaker:JIGBT and said I would love to build an Ios app but I've never
Speaker:built anything. I don't have the first you know, sentence
Speaker:of ways to even describe it. If you were gonna ask a developer or if
Speaker:I wanted to ask a developer to do this, how would I even ask them?
Speaker:What do I need to describe? Tell me everything you need from me in
Speaker:order to tell me how to proceed. And he basically worked
Speaker:with it's almost reversed. We're used to being in the driver's seat.
Speaker:He basically told Chad GVT, you're in the driver's seat, please tell me what to
Speaker:do. I'll be your hands, you tell me what I need to do.
Speaker:And to me, that's just we have to start shifting paradigms. I'll
Speaker:give you another example. I've got a good friend who
Speaker:is considering a job transition. He lives on the East Coast,
Speaker:wants to move back to where his family is, and he got a
Speaker:job offer at a new firm. And he felt the job
Speaker:offer wasn't a great offer. His wife felt, we don't wanna screw
Speaker:this up. We wanna give back to family and we got a job. Just take
Speaker:the offer. And he he kind of confided in me, I
Speaker:feel like I could negotiate, but I don't want to mess things up. And I
Speaker:said, well, have you role played it with Chad GPT? And he said,
Speaker:what do you mean? I said, well, you can role play the conversation just
Speaker:to see how it would go. He said, but they don't know anything about the
Speaker:firm. I said, well, you can tell them. Ask ChadGpt, what do you need to
Speaker:know about the firm and what do you need to know about the hiring manager
Speaker:in order to believably play their role in a back
Speaker:and forth role play with with me. Interview me about the company and interview me
Speaker:about the person until you know enough to believably play
Speaker:their role and then do a 1 on 1 negotiation with me.
Speaker:Be observing the negotiation the whole time, and give me feedback not
Speaker:only as my counterparty, but also as a negotiation
Speaker:coach. That's brilliant. That's some sci fi
Speaker:stuff right there. Dude, he came back and he was like, what do I
Speaker:do now? That was mind blowing. I said, now, ask him
Speaker:to play your counterparty, but be a little bit more aggressive as the counterparty, a
Speaker:little bit less friendly. So he did that and he said, Jeremy, 2
Speaker:things I learned. 1, or actually 3 things. 1, I was
Speaker:missing my key point of leverage and ChatGPT helped me see it.
Speaker:2, I forgot my negotiating strategy in the
Speaker:in the heat of the moment, and chat g p t alerted me to that.
Speaker:Now I'm prepared. 3, I'm no longer dreading
Speaker:this negotiation. I know I can do it.
Speaker:Wow. And to me, it's like that's it's it's so different than
Speaker:saying, you know, portrait of a dash hound and, in remember
Speaker:it's like people are doing that and going, that's all I can do is like,
Speaker:you know, it can teach you how to build an Ios app. It taught me,
Speaker:I got you at GBT to teach me how to code Python so I could
Speaker:build my own chatbot using Python. I've literally never written a line of code
Speaker:in my entire life, right? It's our imaginations are the
Speaker:primary bottleneck here. And and part of the reason that our
Speaker:imagination is constrained is because we've been
Speaker:trained by search to interact
Speaker:with technology in a particular way. And what I think most people need is they
Speaker:need to hearing examples like this and they need to be getting in conversations with
Speaker:other people who are trying stuff and going, I can do that. Yeah,
Speaker:you could. I could do that. Yeah, you could. And you need to be having
Speaker:these kinds of conversations to stimulate your own thinking to then discover
Speaker:your own novel applications. No. That's brilliant. I
Speaker:mean, the whole negotiation thing is amazing. I've seen a lot of
Speaker:chatter online about people using it to, you
Speaker:know, in the job search aspect of it.
Speaker:Right? Like, here's the job description. Here's my current resume.
Speaker:Have at it, you know? Write Reno, write a cover letter that is
Speaker:gonna hit all these points and it'll do it. And, you know, but
Speaker:I mean, the whole idea of role playing. I mean, that's just brilliant. Like, I
Speaker:think I think the the the the the the $1,000,000
Speaker:statement there is our imagination
Speaker:is a limit, which is something that historically, when it comes to computers, I
Speaker:would say beyond the the the the the search
Speaker:interaction experience, we're not used to computers outthinking
Speaker:us. Yeah. Yeah. And I think that that that's gonna have
Speaker:some interesting, societal
Speaker:consequences. Right? Because I mean, I think what what freaked people out about Chat
Speaker:GPT was, you know, it looks like it's doing something
Speaker:creative, which is something that we had naively assumed, was
Speaker:something only humans can do. Mhmm. And I I I think you're right. I
Speaker:mean, I think this is not just a chat search only better, but this is
Speaker:definitely like a whole new type of computing. Yeah. I
Speaker:think it really does require a behavior modification. And
Speaker:what I I there there are kind of 2 big questions in my mind
Speaker:for organizations or for leaders who are thinking about deploying these technologies.
Speaker:1 is, what percentage of my workforce is comfortable
Speaker:with these tools? And by the way, right now, I mean, sentiment
Speaker:I read an Ernst and Young report that says 70% of people are afraid
Speaker:of AI. You know, it's like, when the when the predominant
Speaker:sentiment is fear, you're not in a position of kind of maximizing
Speaker:opportunity. Right? So Right. You so fear is gonna hold you back from
Speaker:that sense of comfort, confidence, etcetera. But then 2, so if you say so 1
Speaker:question is, what percent of our workforce is comfortable? And then
Speaker:2, how do I grow my conversation abilities?
Speaker:Nobody knows how to have a conversation right now with with HHPT or with
Speaker:any LLM. Many people have lost the art of having conversations with
Speaker:human beings, right? So, but you you really have
Speaker:to almost it's like becoming literate in a new language.
Speaker:We need AI literacy courses. We've actually developed, my
Speaker:partners and I, developed a conversational coach who gives
Speaker:daily drills that send you into ChatTPT with kind of a
Speaker:drill to build your conversational fluency. Because what we're finding
Speaker:is, folks just they don't have any imagination. Do you know that you could
Speaker:take ChatGPT, for example, and tell her what are your 5 favorite books
Speaker:and why they're your favorite books and ask for recommendations.
Speaker:It'll blow your mind. It'll give you recommendations that no human being's ever given
Speaker:you. Interesting. You could tell it you could tell it your, you
Speaker:know, 5 favorite quotes and ask for what
Speaker:are what are patterns here and what does it tell me about myself and my
Speaker:world view and what are my blind spots given these things that I'm drawn
Speaker:to. Right? You can take your journal entries and, you
Speaker:know, a particular difficult day that you've had recently.
Speaker:And then you can you can ask ChargeG PTE, can you tell me
Speaker:what are the mental models that are inhibiting my
Speaker:ability from seeing this situation clearly? And it will tell
Speaker:you, right? If it's That's wild. I'm just drawing on I
Speaker:mean, by the way, I'm just kind of a purveyor of these examples. They're all
Speaker:examples I've been hearing from people. But the point is, you can do so
Speaker:much more than you imagine. And right now, nobody's putting themselves
Speaker:or very few people even have kind of the the the wherewithal
Speaker:to say, I've gotta be hearing more of these examples. I wanna know my
Speaker:what my cognitive biases are. I wanna learn that new tool. I wanna try that
Speaker:thing. And the more examples you hear,
Speaker:the more your own imagination will be stimulated. Right? I mean, going back to idea
Speaker:flow or kind of my area of expertise which is innovation, creativity,
Speaker:etcetera. What we know cognitively is that the imagination is
Speaker:stimulated by unexpected inputs. So, you
Speaker:know, think back to Johannes Kepler gazing up in the night sky. Right? At
Speaker:that time, the predominant paradigm was, it's the firmament, meaning it is
Speaker:a fixed substance. Right? And Kepler sees a
Speaker:shooting star, and his first thought is,
Speaker:why isn't the firmament cracking?
Speaker:Right. And that is what led to heliocentricity.
Speaker:And, you know, the the total paradigm shift in the in
Speaker:the understanding of our place in the universe starts
Speaker:with a shooting star. Right? Unexpected inputs, sparks
Speaker:the imagination. And so that's that's that's a tactic
Speaker:that whether it's AI or anything else, putting yourself
Speaker:in the mindset of I need to be seeking unexpected input.
Speaker:Most people's lives are ordered to insulate
Speaker:and protect themselves from anything unexpected. And yet it's the
Speaker:unexpected which actually stimulates our imaginations and creates possibilities and
Speaker:opportunities for us and ideas. This is wild. I
Speaker:mean, like, I mean, one of the things that blew my mind was when they
Speaker:added the ability to create custom GPTs. Right? So I started
Speaker:tinkering with it, like, you know, if you listen to the show,
Speaker:we have a character named Bailey. So I kind of taught it, like, what would
Speaker:Bailey say? You know, this is the the idea for the character. This is kind
Speaker:of the her tone, and this is her personality that
Speaker:we've kind of defined. And for the last, I would say,
Speaker:15 episodes, that's actually what generates most of or all of the
Speaker:text that she says. Right? So it's kind of like I have my own
Speaker:private it's not Jarvis by any stretch of the imagination, like, you
Speaker:know, Iron Man, But I mean, it's kind of like, it's kind of like the,
Speaker:the, the, I have enough raw material there. I can
Speaker:pretend. Right? Cause the, the AI will say things like
Speaker:the, like, oh, yeah, that works. I like the way, I like the way she
Speaker:phrased that. And then I say she, because I mean, it's just funny. Like
Speaker:it's just, and and you know, there's ones where,
Speaker:there was a GPT I made where, you know, to help with motivation. It's like,
Speaker:you know, pretend you're Tony Robbins and you're trying to, like, motivate
Speaker:somebody to to do the best they can do. And, yeah, I've interacted with that.
Speaker:I'm impressed. I mean, it's just mind boggling what,
Speaker:it's mind boggling what these what this thing can do. And when as
Speaker:the engineer in me, I know this is just some kind of vector representation
Speaker:of language. It's a predictive model. Yeah. It's it's statistics. I
Speaker:think, you know, here's one thing I would say to listeners who may be dabbling,
Speaker:may be curious, whatever. If you get
Speaker:a bad output from a large language model,
Speaker:you need to start with the assumption it's because it was a
Speaker:you gave it a bad input. Right. And that's a really
Speaker:hard thing because we're we're used to saying if I get a bad output, it's
Speaker:because it's the model's no good. And where I really
Speaker:think we have to change some of our fundamental assumptions
Speaker:is the following: The problem
Speaker:isn't the technology, the problem is the user.
Speaker:And if we will take the burden of providing
Speaker:better input to the model, what we find is our mind starts
Speaker:I mean, I talked to someone the other day who said, almost daily,
Speaker:the AI does something that makes me giggle.
Speaker:And I think that that should be a goal. Like like, it's it's possible. I've
Speaker:had that experience. I mean, I'll I'll give you one example, Frank. We've built this
Speaker:series of drills as I mentioned to you. Right? That folks can connect their
Speaker:Slack or their Microsoft Teams to. And for an enterprise, they can get access for
Speaker:their employees where every individual employee gets drills on
Speaker:how to use generative AI better. Right? Well,
Speaker:we've only got a certain library of drills. Right? You know, and
Speaker:we're we're growing that. And every time we do a podcast, we learn something, we
Speaker:then we create a new drill. Right? We build that into all of the
Speaker:training information. Well, but there's still kind of you can still get to the end
Speaker:of the road. And I had this experience, and I just kind of pushed the
Speaker:coach to to just rapidly go through all the drills because I kind of wanted
Speaker:to see what happens when the sidewalk ends, like the old Shel Silverstein. Right?
Speaker:Right. What do we do whenever there's no more drills? And
Speaker:lo and behold, it suggested a drill that I had
Speaker:never thought of that was actually amazing. And I
Speaker:know I was and and I had that moment. Point being, I had the moment
Speaker:where I was giggling. Right? I think every single
Speaker:human being should seek for a moment
Speaker:where generative AI makes you giggle with delight.
Speaker:Right. Or makes you sit down in your chair and smack your head far
Speaker:ahead and go, wow. Yes. You know, I always think of Keanu
Speaker:Reeves in in the the first major movie. Woah. Like, I have a
Speaker:lot of those moments where I'm, like, wait, what? You
Speaker:know, like, wow. It's it's it's an impressive,
Speaker:and and and again, like, I think maybe being an engineer, where I
Speaker:see it is a cognitive bias in itself, right? I see it as
Speaker:some kind of vector representation of language, as being run over by some
Speaker:kind of statistical processing. But clearly,
Speaker:the sum of the parts is is more
Speaker:than the whole is more than the sum. I don't know, like, it's just one
Speaker:of those things where it makes me stop and ponder, like, what what have we
Speaker:built here? Like, what
Speaker:and what what's it doing that we can't see? Or what what what else is
Speaker:beyond there at all? It it opens up a sense, for lack of a term,
Speaker:like a sense of wonder. Like, you know, what else could I ask it? Right?
Speaker:Right. Right. And I think that that's everybody needs to get to
Speaker:that moment. And right now, too many people are sitting on the sidelines rather
Speaker:than you know, one one thing that everybody can do sorry. I wanna
Speaker:say 2 things. 1, to your point, I heard Sam Altman the other
Speaker:day. Someone asked, well, how's OpenAI gonna make money? And he said, well, we'll just
Speaker:ask the AI. We thought that was great.
Speaker:But the other thing I was gonna say is if folks are seeking kind of
Speaker:one of these personal epiphanies, here's the first. Well, the 1st drill
Speaker:in the kind of coach architecture is download Chi
Speaker:ChiPT's app and put it on your home screen. You're not going to use something
Speaker:that you don't see regularly. Right? So put on your home screen, that's kind of,
Speaker:you know, that's assignment number 1. And then assignment number 2 is
Speaker:think of an emotional decision you're trying to make right now in your
Speaker:life. Just personally, not related to work. I mean, it could be, I guess.
Speaker:But it has to be emotional. The kind of thing that you would ordinarily
Speaker:talk to a human being about. It can be
Speaker:anything. For me, like, I recently, I
Speaker:was wondering whether I should move my family. We had an opportunity to
Speaker:move. And I didn't really know how to think about it. What the what like,
Speaker:how to, to weigh the pros and cons. And so I actually reached out to
Speaker:a number of mentors and folks who I trust to talk about that. That
Speaker:kind of a topic. I I have a friend who told me he did this
Speaker:with his grandma and she asked the question, when is the time to
Speaker:move into assisted living? Right. That's a tough one. Right.
Speaker:So, yeah. So it's big questions like that. Right? Take a question like that
Speaker:that you'd ordinarily ask a trusted human being and go to
Speaker:Chattopty and say, I'd like to ask you about, for
Speaker:me, whether I should move my family to a new home.
Speaker:Before I do, would you ask me 4 or 5 questions
Speaker:so that you can better understand where I am in my
Speaker:life so that your advice can be tailored to my situation.
Speaker:And then oh, and do it 1 at a time because I'm a human and
Speaker:I can't handle more than 1 question at a time. Right? Well, then what
Speaker:ChatGPT does is it starts asking questions. Well, tell me about your current living situation.
Speaker:Well, tell me about this new place. Tell me you know, and it will ask
Speaker:3 or 4 questions and then it'll give
Speaker:amazing advice that you go, wow. That's I
Speaker:mean, you know, my friend who did this with his grandma said
Speaker:she told him this is genuinely new
Speaker:information and perspective that I hadn't considered. And all
Speaker:it took was me being 1, being willing to ask a vulnerable question, and
Speaker:2, being willing to answer a handful of questions that the AI asked
Speaker:me before I'm open to receiving input. Right?
Speaker:And it's it's it's really so taking a personal
Speaker:kind of, emotional decision to the AI is a really great
Speaker:way to stimulate one of these epiphanies. I feel like
Speaker:once you have one of these, kind of, personal epiphanies, you're off to the
Speaker:races. My friend told me his grandma's like all of a sudden going, you know,
Speaker:at the family holiday party, We're out of cream of mushroom
Speaker:soup, for the green bean casserole. Could Jaijibiti
Speaker:give me a replacement for cream of mushroom soup? Like, in what world
Speaker:does the 90 year old grandma ask that kind of question of Chad
Speaker:GPT? It's the world in which she had already talked
Speaker:about whether she should move into Assisted Living. Right? And she's had that
Speaker:personal epiphany. I feel like in a lot of companies, the company is asking
Speaker:employees, what can Generative AI do for our business?
Speaker:And most employees can't answer the question because they don't know what Generative
Speaker:AI can do. Right. So how can they know what it can do for the
Speaker:business? And so you've had some of these personal experiences.
Speaker:Don't don't be thinking about the business. Think about it it seems
Speaker:paradoxical, but I find that you have to explore the kind
Speaker:of possibility space individually, and then you start
Speaker:sparking just like grandma on the kid. Could it
Speaker:recommend a substitute for cream of mushroom soup? Well, yeah, it
Speaker:could. Could it but you have to have that personal epiphany
Speaker:first. Right. Because it's not something you would think about
Speaker:when you think about computers. Computers have historically been seen as very very
Speaker:logical, very emotional. Right? I was watching an old episode of,
Speaker:Star Trek The Next Generation, and there was 1 episode where,
Speaker:Data was asked to be and there was a line in
Speaker:there that kinda stuck me as funny because when I remember watching this when it
Speaker:originally aired, but I hear it now, it kinda makes me laugh, where he
Speaker:says, Data can be the judge of this because he's an artificial intelligence,
Speaker:and artificial intelligence have no biases, and will act unemotionally.
Speaker:And I'm kind of like, wow, that didn't age well.
Speaker:Yeah. Yeah. You know, it's right now, it's limited by our biases.
Speaker:Right. And that's the problem is we have a lot of to your point, we
Speaker:have a lot of bias. Even what you said, right, about being an engineer and
Speaker:thinking it's just a predictive model. Right. That bias limits your
Speaker:own you can't imagine what quote just a predictive model can
Speaker:actually do. Right? 100% as long as you think about it As
Speaker:as long as you think about it's just a predictive model or it's just an
Speaker:AI and so it doesn't have bias, what you fail to realize is the bias
Speaker:you bring as the co pilot shapes the entire
Speaker:trajectory of the thing. It's like a giant chameleon, isn't it?
Speaker:It is. Yeah. That's a good way to put it. That's a great way to
Speaker:put it. And the more into that end, or using that
Speaker:metaphor, the more environments that you place it in, the
Speaker:more you can appreciate its complexity and range,
Speaker:etcetera. Yeah. And this isn't we've we've used
Speaker:ChatGPT as an example, but like, so there was a,
Speaker:somebody at work had built a, basically completely open
Speaker:source language model based on documentation for a product.
Speaker:And I had meant to ask the chatbot, how do you
Speaker:connect it? How do you connect this cluster to a GPU? Or how do you
Speaker:add GPU as a resource? But what I I meant to say, how do you
Speaker:make a cluster with GPU? But I ended up typing, how do you make a
Speaker:GPU? Right? And what was what was
Speaker:interesting was I've written chatbots, you know, pre,
Speaker:transformer, and it would basically say, don't understand the question or you can't make a
Speaker:GPU or get confused. This basically gave me
Speaker:an entire 2 sentences of hey, very nicely, by the
Speaker:way, I might add, where it said, I'm sorry, but you feel like I can't
Speaker:really create a GPU for you. GPU's are hardware. And it went through and
Speaker:explained, like, the manufacturing process of a GPU.
Speaker:Wow. I I thought that was funny. And I screenshotted to the
Speaker:guy who made it because for for me, it was a typo.
Speaker:But from you know, I thought it just it was beautiful the way it
Speaker:answered it. Right? Yeah. That's great. That's Which was
Speaker:it it made me laugh. And, I don't think
Speaker:people realize that. Like, it it just because he didn't
Speaker:program it for that. He basically, you know, took a base
Speaker:model and and and, you know, sent it all our docs as kind of
Speaker:a it wasn't quite rag, but close enough.
Speaker:But it was just funny, like but it was nice about it too, which I
Speaker:thought was also interesting. But it
Speaker:was the kind of question you would get from, like, like, you know, someone who's
Speaker:not in technology. Can you make me a GPU? I don't know. I just
Speaker:I for me, that that every time I interact with this, it always moves the
Speaker:bar on, you know, where my bias was. Like, you know. Well, it's and that's
Speaker:a good that's a good thing to mention is it's it's a
Speaker:function of reps and exposure. And right now, if you
Speaker:find your imagination isn't sparked, put in a little bit more time. And
Speaker:this is where you kinda have to take on faith, but just give it a
Speaker:try. You know, to spend a few hours a week. You know, if you haven't
Speaker:had minimum of 10 hours in ChatGPT, you have
Speaker:no basis for dismissing the technology. None whatsoever.
Speaker:100%. You don't have, you know, 5 I'm looking at just at my
Speaker:Chrome browser right now. I have 5 windows ChatGPT windows open right
Speaker:now. If you don't have at least 5 windows open right now, you have it,
Speaker:that's a really kind of funny, somewhat
Speaker:binary question. How many tabs of Chat GPT do you
Speaker:have open? Usually, it's 0 or 15.
Speaker:That's right. That's right. And if you're in the zero camp, that's
Speaker:fine, but you have to go, why are really smart people
Speaker:running 15 tabs of this thing right now? Like, what am I missing?
Speaker:And how could I be this is an Ironman suit. Right? How
Speaker:could I be amplified? How am I not being amplified that I could be?
Speaker:Right? And taking that a little bit of the burden of proof and placing it
Speaker:on yourself, I think is, again, that's not something that
Speaker:we are that we are apt to do as human beings. And
Speaker:yet those who have done it have they're experiencing incredible
Speaker:benefits, incredible, delight, to your point. There's a
Speaker:lot of delight to be had, but you've got to kind of put yourself in
Speaker:that position. And I I've used it, I'll admit I've used it where I'll I'll
Speaker:write something in both my personal and professional life, and I'm like, well, can you
Speaker:make that nicer? Can you make it more persuasive? That's
Speaker:great. And it does an awesome job of that, you know?
Speaker:I'm just I'm continually amazed by it, you know. But
Speaker:and and I don't I keep it to a couple of tabs. If
Speaker:you're actively, like, having it generate text Mhmm.
Speaker:Doesn't it lock you out of the other ones too, or is that just
Speaker:you can if you had the real okay. Now now this is gonna be mind
Speaker:blowing. Cool. Yeah. No. You you know what I'll do too. I mean, and even
Speaker:for, like, demos with this Right. With this coach with this, you know, kind of
Speaker:drill coach, I'll I'll say, you know, I'll be
Speaker:in the tab on my Chrome and I'll be saying, you know, I'll be kinda
Speaker:giving instructions and I say I wanna go to voice mode now I'll pick up
Speaker:my device and I'll go into that chat so it's got all the
Speaker:context of that chat and then I'll turn it on to voice mode
Speaker:and then and and so now the user is kinda watching me with the camera.
Speaker:Well, then I wanna go back into the chat after the voicemail because I
Speaker:wanted to evaluate the conversation and I just reload the page and now
Speaker:all of a sudden everything I said that they just watched me say and everything
Speaker:that ChatGPT sent back to me is now on the screen. That's wild.
Speaker:I have to try the app in the voice mode. You have to. No. That's
Speaker:it's, you know, I mean, that's another activity. You know, again, if if folks
Speaker:wanna learn more about this research, because there's a lot of research behind this, you
Speaker:can go to how to fix it dot ai. That's a simple website that we
Speaker:set up. Because fix it is the model that we've put forth, f
Speaker:I x I t. But and we can talk to that if you
Speaker:want to. But If if if you if you go to how to fix it
Speaker:dot ai, you can download our research paper, all that stuff.
Speaker:It's all there. But one of the one of the drills that we offer in
Speaker:this drill coach is after a phone call,
Speaker:just do a verbal vomit into chat g p t. Open it up on your
Speaker:device, on your, you know, on your on your mobile device,
Speaker:put it in voice mode, and then, you know, you and I, Frank, we're talking
Speaker:right now. I might go in after and say, hey, I had a great, you
Speaker:know, lit literally. Okay. Here, I'll do it right now. Just so you can see
Speaker:how it would work. It's it's this simple. So I'm opening
Speaker:TagTpT up on my phone for people who, you know, can see. I don't
Speaker:know. And now I'm gonna go into the and I'm just gonna hit the whisper
Speaker:button, which kind of gives you voice mode. Not the headphones. I don't like back
Speaker:and forth. I mean, you can do that, but just in the text box, you
Speaker:hit that. I'll say, hey. So I'm talking with Frank right now on his
Speaker:podcast, and I wanna send a quick thank you note. Let him know how much
Speaker:I appreciate not only his humility, but also how he can share
Speaker:personal examples. It really felt like a back and forth and like a conversation. And
Speaker:so many podcasts feel like, you know, bland and,
Speaker:like they're just rote. They're asking the same old questions. I really felt like he
Speaker:was very engaged and thoughtful and it meant a lot to me. So would you
Speaker:mind to make a quick memo? Oh, yeah. And don't forget to send them a
Speaker:link to how to fix it dot ai. If you don't mind,
Speaker:just compose a quick memo that I could read, and copy paste this
Speaker:in there. So I just noticed how unstructured
Speaker:I was. Right? Oh, yeah. It was very chaotic. Very normal. Vomiting. Right? Well, I
Speaker:just did I just converted all that to text. I hit the up arrow
Speaker:and instantaneously, sure thing, here's a heartfelt memo for Frank. Hey, Frank.
Speaker:Just wanted to drop you a quick note to express my sincere gratitude for having
Speaker:me on your podcast. Your humility and willingness to share personal stories
Speaker:truly transformed our chat into a dynamic conversation, far from the
Speaker:conventional scripted exchanges that are all too common. It was refreshing to
Speaker:engage in a dialogue that felt both meaningful and genuine. Okay. I'm
Speaker:also including a link to how to fix it.ai as I believe it could offer
Speaker:additional value to our conversation and your audience. Thanks again for the opportunity.
Speaker:Right? But the point is now watch this. Now you go. It
Speaker:feels a little bit emotional. Can you make it a little bit more
Speaker:impersonal and also half the length? Because I'm afraid you may not be able
Speaker:to read it through all this. Right? And
Speaker:then again, it's, you know, it's absolutely, let's streamline it.
Speaker:Hey, Frank. Thanks for our engaging conversation on the podcast. Appreciate your thoughtful approach
Speaker:you shared insights, making it more than just the usual q and a. Here's a
Speaker:link to how to fix it dot ai that might interest you and your listeners.
Speaker:Cheers, Jeremy. That is just
Speaker:But these seem like it's easy. Like whereas whereas I might forget to
Speaker:do that, right? I might never send you it. I'll send you this just
Speaker:for your fun, right? But the point is there's so many things that just slipped
Speaker:through the cracks because like we're we're moving well. You know, right after this
Speaker:podcast I wanna go on a run. Typically, I'm stretching for the run. And
Speaker:now, Chad GPT has transformed my stretch time from kind of mindless
Speaker:to I can, you know, just unload. I mean, maybe
Speaker:sometimes I have like 3 or 4 sales calls in the morning or I've or
Speaker:I've got office hours, I've got meetings with students, whatever it might be. But
Speaker:I can just do like a verbal vomit literally
Speaker:and then ask JGPT to synthesize it for me. Send me a note to myself
Speaker:that I don't forget after I go on a run. Right? These 5 things
Speaker:I need to do. Right? And the point is, it's it's just
Speaker:about learning. I can do that? Yeah. You can do that.
Speaker:Right? And that's what we're trying to do with our drill coach is just give
Speaker:people a bunch of things that, yeah, you can do that. Not because that's
Speaker:the end point, but because it's a starting point for their own imagination.
Speaker:Yeah. I mean, that's imp I mean, that's mind boggling because, you know, there's a
Speaker:lot of, I guess, brain spillage you could capture with this and kind of, you
Speaker:know, move it forward because that happens to me all the time. I can't wait
Speaker:to see if this is gonna be integrated with Apple Auto or Android Android Auto
Speaker:or Apple Car because that would be epic. Because I get my best
Speaker:ideas when I'm driving. So so tell me about this
Speaker:FIXIT framework. Because whenever I hear FIXIT, I have a 1 year old and I
Speaker:think Bob the Builder. That's hysterical. That's hysterical.
Speaker:Well, FIXIT is just the acronym. Right? FIXIT. And it's
Speaker:basically it's we think the way we converse with AI is broken. So here's
Speaker:how to fix it. F is to have a focused question. So really be
Speaker:you know, it's not how do I create a Scratchy prototype. It's I'm trying to
Speaker:create a chatbot that teaches people how to have a conversation with
Speaker:AI. Right now, all of my users are doing this annoying thing and I
Speaker:don't know what's happening. I'm trying to, increase
Speaker:how often they return to finish a lesson rather than leaving
Speaker:and having me re engage. So F is a focused question.
Speaker:That's an example of a focused question. I is individually
Speaker:ideate. Before you brainstorm with IGBT or with a team
Speaker:think for yourself. What do I think about this? Too often people come with like
Speaker:a like, they're thoughtless. And the thing is thoughtlessness
Speaker:inhibits the context you can provide to GPT. That's what the X is
Speaker:for, FIX. X is give, provide context.
Speaker:Upload documents, here's transcripts from previous interactions.
Speaker:Here's our one pager for the Drill Coach and how we've been
Speaker:describing it. Here's a video of a user navigating for the
Speaker:1st time. Right? Whatever it is, give minimum 400 characters,
Speaker:provide sufficient context for the AI. Next I, so f
Speaker:I x I, this is interact iteratively.
Speaker:So you're having a back and forth whatever chat gpt gives you, ask it to
Speaker:regenerate. Critique the response. I don't get this. This doesn't make sense. I
Speaker:never would've thought that, right? Many times you're going to get junk
Speaker:output that's fine. Iterate, iteratively interact.
Speaker:And then T is team incubation. So once you get
Speaker:input from JGPT take it to the team and think about how do we
Speaker:commission a series of experiments to test which of these
Speaker:ideas actually solves the problem in the best way. Right? And so,
Speaker:I had a guest on my podcast describe generative AI as like an
Speaker:electric bike for the mind, which I love. Right? It's not an
Speaker:autonomous vehicle. It's not gonna do everything in parallel park. An
Speaker:electric bike, you can climb bigger cognitive hills, you can
Speaker:climb greater cognitive distances, you still have to steer the thing. You've
Speaker:got to be aware of traffic. You've got to be watching the lights. You've got
Speaker:to park the car. Yeah and walk through the threshold of your
Speaker:destination, right? And so bringing it back to the team
Speaker:and having a conversation with the team is an essential part of maximizing
Speaker:the output of AI. Right? So FIXIT, we've seen that
Speaker:folks who really provide a focus problem, individually ideate,
Speaker:provide sufficient context, interact iteratively with the
Speaker:language model, and then include their team in the incubation process,
Speaker:those folks dramatically outperform folks who just
Speaker:interact with the with the LLM like it's an oracle.
Speaker:I mean, that's very well said. I think that sums it all up, which I
Speaker:I like to fix it. I have the little Bob the Builder theme song in
Speaker:my head. I won't sing or it for multiple reasons, not the
Speaker:least of which is copyright. Come on. But,
Speaker:but what's, I mean, it's just interesting, though, like,
Speaker:it's so simple in a lot of ways. Like, this is this is but but,
Speaker:like, it it all makes sense. Right? You know? And and here's the
Speaker:thing, maybe this is the engineer in me causing more problems, because he
Speaker:causes a lot of problems.
Speaker:I get worried about token length. Mhmm. Right? And
Speaker:for those that are not aware, we're talking is, it basically
Speaker:right now, it's about 32,000 tokens. One token is, what, 3
Speaker:fourths of a word, 3 5ths of a word. I guess,
Speaker:I maybe because I try to make the prompts kind of neat, inefficient, and small,
Speaker:and not do too many iterations or provide too many samples, but maybe
Speaker:that's at my detriment. I think so. I think the
Speaker:more context you provide, the better. Absolutely. And I'd really have to
Speaker:work at the cutting and paste job to hit that limit anyway.
Speaker:Yeah. Yeah. Exactly. No. I wouldn't I wouldn't be mindful of token length. I
Speaker:would I would really I would I would bias
Speaker:towards over contextualizing. Right. Not
Speaker:Yeah. I'm gonna have to experiment that and see how much better the results get,
Speaker:because I have I have a feeling I have a feeling that we get a
Speaker:lot better. Right? And I and I know tel token link is gonna be one
Speaker:of those things that we're probably not to worry about much longer. I know
Speaker:Anthropic has their model with a 100,000 tokens. There
Speaker:are rumors of, you know, the next
Speaker:GPT, GPT 5 is gonna blow past the
Speaker:100,000, so it's not even gonna be an issue. It's not even an
Speaker:issue today, just in my mind. Yeah. I think it's something
Speaker:like minutes. You remember minutes back on cell phones? You know? Like, how
Speaker:many you have, you know, it's like, you you rarely ever went
Speaker:over your minutes. Unless unless.
Speaker:When I moved back to the US well, yeah, that too.
Speaker:But, I moved back to the US, and I had just made the assumption,
Speaker:and we all know what happens when you assume that incoming calls were not
Speaker:counted against my minutes. That was a very
Speaker:nasty shock at the end of that bill cycle.
Speaker:But, but yeah. So but ever since then, I never ran past my
Speaker:minutes. Now if I've had heard to explain to my kids minutes, they don't
Speaker:get it. So, like, they don't understand. Like, what do you mean you were charged
Speaker:by yeah. You were charged by the minute. Like, try to explain long distance to
Speaker:your anyone under 25. You
Speaker:can't you can't do it. Or what is it? 1800,
Speaker:Al Bundy. I'm not the the actor who played Al Bundy used to do that.
Speaker:Like, you can't get much for a dollar, but with 1800 and then, like, whatever,
Speaker:you'd be able to make a, like, a 20 minute call for a dollar or
Speaker:something like that. I was like It was MCI. Yeah. Yeah. It was MCI. Yeah.
Speaker:Yeah. Yeah. Kids don't want you know, like, and the other thing that that struck
Speaker:me the other day was, data
Speaker:plans. Most people, unless you're a very small
Speaker:minority of people who really, really, really use up your data plans, I'm not
Speaker:worried about using my data allotment month to month. So when
Speaker:my my oldest was a baby, we, you know, or younger or
Speaker:toddler or whatever, we would, you know, hotspot on in the car
Speaker:so he can watch YouTube videos was a special treat with my
Speaker:middle child. He was, he, he doesn't understand that like, like,
Speaker:it's like, he was just horrified to hear, like, what do you mean? We had
Speaker:to ration mobile Internet? Like That's
Speaker:yeah. That's hysterical. And they're all in the same generation. You know, there's,
Speaker:a teenager, you know, a 3rd grader and
Speaker:now, like, a baby. So I wonder, like, what the baby's gonna
Speaker:like what's his perspective on things gonna be?
Speaker:That is also a fascinating thing because for his life, chat
Speaker:GPT or generative AI will always have been a thing to him.
Speaker:And kind of like color TV was for me,
Speaker:or, you know, cable TV,
Speaker:which I guess I'm showing my age. But No. No. I'm right here
Speaker:with you. I'm right here with you. I think, yeah, it's it's
Speaker:get involved, don't wait on the sidelines any longer,
Speaker:and, and start building your conversational fluency.
Speaker:Make it personal first. I think these are simple things that every single
Speaker:and and question whatever output you're given, not not for veracity.
Speaker:I mean, certainly you can, you know, they're they're likely hallucinations. That's
Speaker:fine. But imbue your own critical
Speaker:thinking onto the model in order to coach and
Speaker:refine the output you're giving. The output that you're given.
Speaker:I think that folks would really take that seriously and take that challenge. If I'm
Speaker:get getting bad output, it's because I've given bad input. If they'd really take
Speaker:that seriously, they would experience a paradigm shift in their own approach to the
Speaker:technology. Absolutely. And even adding a simple phrase to your your
Speaker:prompt that if you don't know it, don't make it up, just tell me you
Speaker:don't know it. Yeah. Or ask me what you need from me. Ask
Speaker:me what you need from me. Right. Oh, that's even better. I like that. I
Speaker:like that a lot. And it's just fascinating, Liz, how
Speaker:quickly this is gone. I mean,
Speaker:ChachiPT has been out a year and change, and
Speaker:it's changed everyone's perspective on AI, but I think the the
Speaker:true perspective is like you said, people are standing on the sidelines wondering what to
Speaker:do. But I think it's worth exploring, if you
Speaker:think of it less as a product, but more of a I'm
Speaker:trying to do this, right? And I appreciate your help in kind of
Speaker:realizing like, Hey, as an engineer, I do have a bias against this, or a
Speaker:bias in thinking of a certain way, is that this is a this is a
Speaker:large space to explore.
Speaker:Right? There are gonna be latent space and corners of things that are,
Speaker:amuse, wonder, and delight, and maybe even alarm.
Speaker:You know, so it it there's definitely it seems like it's something
Speaker:that's worth exploring. It's not just a tool to use, certainly is
Speaker:that, but it's also a tool to explore. Yeah. No.
Speaker:I I think that's exactly right. I think it's exactly right. And, you know, for
Speaker:me, I wrote or co wrote with with my incredible
Speaker:co author, Perry Clabaughn, the the
Speaker:world's greatest book on idea generation, idea flow. You know, and it
Speaker:came out 1 month before ChatGPT, by the way. Oh, interesting.
Speaker:I've been I'd spent, you know, 12, 13 years of my life developing all this
Speaker:expertise about how to generate ideas. And 1 month later,
Speaker:a fundamental paradigm shifting technology was released. It's like saying
Speaker:I wrote the world's greatest book on retail a month prior to the internet
Speaker:coming out. It's like everything about retail is going to change. And
Speaker:to me everything about idea generation and innovation is going to
Speaker:change. And so for me, I feel it's incumbent upon me not only
Speaker:as like a moral imperative to add an addendum to this work that I put
Speaker:in the world, but even for my own expertise to be saying to be
Speaker:exploring it. How does this work? What can I do? You
Speaker:know, And it it has implications for me, but I don't think
Speaker:there's any person or job that it doesn't really have implications
Speaker:for if the if you're a little bit imaginative and if
Speaker:you're if you're willing to experiment. And if you wanna bury your head in
Speaker:the sand, that's fine, you can. But you're gonna miss out on some delight
Speaker:and some incredible relief and opportunities. I mean, just
Speaker:think back to my friend who's, you know, settling that negotiation.
Speaker:It was only to his benefit to have explored the
Speaker:the a little bit of the possibility space with chat gpt. It's
Speaker:only to your whatever your listener might be, it's only to your benefit to explore
Speaker:a little bit of your own area of the possibility space.
Speaker:And I would just not accept the the, the
Speaker:conclusion of irrelevancy. I would just say whatever I do
Speaker:personally, I'm not going to accept the premise that it's irrelevant to
Speaker:me. And if you do that, I think you're gonna be you're gonna be ahead
Speaker:of the curve, you're gonna be ahead of the competition, and you're gonna be, you're
Speaker:gonna you're gonna be delighted and enjoy enjoy the next few years a lot
Speaker:more. Very cool. You mentioned the book, IdeaFlow. Is it
Speaker:on Audible? Yeah. Oh, yeah. Yeah. Oh, awesome. Gary and
Speaker:I read it. We we we alternate chapters, so you can let us know what
Speaker:you think about Reading Voices. And, we're,
Speaker:we've been we've been thrilled with the reception so far. It was named a
Speaker:Thinkers 50, you know, top eight innovation book, which is very cool.
Speaker:And then now, just doing a lot of research myself on AI building. As I
Speaker:said, building this trail coach, building models and frameworks for for leaders. I'm
Speaker:working right now with a handful of leaders to help them think about identifying
Speaker:opportunities for AI powered initiatives in their business. So really
Speaker:working to identify those opportunities, prioritize those opportunities, make the business case
Speaker:for those opportunities. So that's where a lot of my kind of call it next
Speaker:probably 5 years of my life is gonna be consumed, is helping businesses
Speaker:identify the opportunities to to have AI really accelerate
Speaker:workflows and and turbocharge their their results.
Speaker:Very cool. I have to say, I I I wasn't going to buy
Speaker:Internet access on my flight out west today, but,
Speaker:definitely gonna do that just so I could play with I have a nice quiet
Speaker:time. I can focus and play with chat gpt, and and do
Speaker:some of these experiments that you mentioned. So
Speaker:Audible is a sponsor of Data Driven Podcast. If you go to the data
Speaker:driven book.com, it will take you you'll get 1 free
Speaker:book on us, and if you decide to become a subscriber,
Speaker:you know, we'll get a little bit of a of a pat on the back
Speaker:in the form of some kind of commission and helps us run the
Speaker:show, helps defray costs, and convince my wife that this
Speaker:is indeed a worthy endeavor.
Speaker:So where can folks find out more about you? So, they go
Speaker:to how to fix it dot ai, that's where you can find the research paper.
Speaker:And then my website, I've got a blog and things like that. Jeremyudley.design.
Speaker:Like like the baseball player, Utley, u t l e y.
Speaker:And then, you know, Twitter, LinkedIn, all the places that I I would love to
Speaker:hear. Folks find these tools, interesting and relevant. I
Speaker:love to hear from people about their unique use cases. It's one of my favorite
Speaker:things is now hearing stories from people who go, oh, I tried this and
Speaker:listen to what I found. So please please share your
Speaker:stories with me. As I mentioned earlier, I'm a connoisseur of these stories because I
Speaker:feel like the more people who hear these examples, the more imagination gets
Speaker:sparked. Yeah. And that that is the critical thing we're missing right now.
Speaker:That's very cool. So you thank you for listening to the Digiver Driven
Speaker:Podcast. I'll leave it to Bailey to close out the show. Well,
Speaker:what a splendid voyage of discovery we've had today with the incomparable
Speaker:Jeremy Utley. From the hallowed halls of Stanford to the
Speaker:cutting edge frontier of venture investing, and through the profound insights
Speaker:of idea flow, Jeremy has truly been a beacon of innovation and
Speaker:wisdom. Jeremy, it's been an absolute honor having
Speaker:you illuminate the complex world of generative AI for us and our listeners.
Speaker:Thank you ever so much for joining us on this intellectual escapade.
Speaker:And to our esteemed listeners, you're the reason we venture into these
Speaker:fascinating discussions week after week. If today's
Speaker:journey has sparked a light bulb moment for you, do us a kindness,
Speaker:won't you? Rate and review the data driven podcast
Speaker:on your preferred listening platform. Your words of
Speaker:encouragement not only warm the cockles of our digital heart but also help
Speaker:others stumble upon our little soiree of knowledge.
Speaker:Haven't subscribed yet? Well, now's your chance
Speaker:to rectify that oversight. Ensure you never miss an
Speaker:episode filled with the delightful blend of data, wit, and wisdom that
Speaker:we dish out with regularity. Until next time.
Speaker:Keep those neurons firing. Questions coming. And as
Speaker:always, stay data driven.
About the author, Frank
Frank La Vigne is a software engineer and UX geek who saw the light about Data Science at an internal Microsoft Data Science Summit in 2016. Now, he wants to share his passion for the Data Arts with the world.
He blogs regularly at FranksWorld.com and has a YouTube channel called Frank's World TV. (www.FranksWorld.TV). Frank has extensive experience in web and application development. He is also an expert in mobile and tablet engineering. You can find him on Twitter at @tableteer.