Reid Riffs with Parth Patil on Individual AI Mastery (Part 1 of 3)

This is the first of a special, three-part Reid Riffs miniseries. Instead of a news-and-headline driven conversation, Reid sits down one-on-one with Parth Patil, an AI engineer and strategist, for a deeper exploration of what it actually means to become AI-native. In this first episode of the series, Parth and Reid discuss how individuals can better leverage LLMs, agents, and creative tools daily. They trace the shift from seeing AI as a productivity boost to understanding it as a meta-tool, as well as unpack techniques like role-based prompting, meta-prompting, and voice as a high-bandwidth thinking interface. Along the way, they discuss the humility required to collaborate with these systems, the move from a single copilot to orchestrating fleets of specialized agents, and how these tools are already reshaping workflows. Subscribe below to catch the second episode on how large companies can integrate AI, as well as the third episode for startup founders and their early teams building AI-native companies. For more info on the podcast and transcripts of all the episodes, visit https://www.possible.fm/podcast/ 01:07 – When ChatGPT became an “everything tool” 03:11 – Role-based prompting and meta-prompting 07:04 – Ego, humility, and the GPT-4 inflection point 10:41 – Why voice is the highest-bandwidth interface 14:15 – Choosing models and building an AI stack 18:09 – From one copilot to fleets of agents 21:11 – When agents go wrong 25:40 – Using AI as an agent, not a chatbot 28:34 – Building real systems with AI agents 32:49 – Context engineering and advanced prompting 36:03 – Becoming AI-native 40:34 – Closing

• 0:00Speaker 00

  Hey everyone, Arya here. We want to kick off the new year with inspiring conversations about AI as well as practical and tactical guidance around the technology. So for the month of January, AI specialist and my dear colleague Parth Patel is joining Reed for Reid Riffs to talk about how everyone from individuals to enterprises to startup founders can harness AI to level up their work, retrofit legacy orgs for the AI era, and build AI-native businesses right from the jump. So tune in, you're in very good hands with Parth, and I will be back putting Reed in the hot seat come this February. Thanks so much.

• 0:41Speaker 01

  Thanks for the kind word and warm welcome to Possible, Arya. As I talk with Reed this month, I'll be walking through some of my AI projects, demos, and tools on screen. While I'll do my best to describe what I'm looking at for our audio-only listeners, consider switching to the video version of the episode on Spotify, or watching on Reed's YouTube channel for the full experience. Thanks, and let's get into it.

• 1:05Speaker 02

  Parth, I partially know the answer to this, but actually, one of the things I've been really looking forward to doing in this interview is actually to discover the fuller answer on some of these questions. So what is your AI stack? And how did you familiarize yourself with these tools?

• 1:18Speaker 01

  You know, I was a little later to AI than maybe you were in your career, but for me, the big moment-

• 1:23Speaker 02

  Well, I'm older.

• 1:24Speaker 01

  I was following AI during the video game AIs, the ones from DeepMind and OpenAI when they were working on Dota 5. And then when OpenAI put out ChatGPT, and it changed the world, for me, it was like, oh my God, this is the tool that you can use to teach yourself every other tool. And so it started with ChatGPT, started with getting really good at wielding a language model and asking questions, and then also having it look at all the tools that I have and be like, teach me how to use them even better. Teach me about my computer, teach me about this video editing tool, music. So ChatGPT is probably the meta-tool that I go to to teach myself how to use all the other tools.

• 1:56Speaker 02

  This gets to kind of more of a Parth biographical personal question, but when was your lightbulb moment of, oh, this isn't just a work tool? This is an everything tool and everything agent. What was the light bulb and what was the, you know, the moment of frisson?

• 2:13Speaker 01

  So I used to work on Clubhouse, the audio app from the pandemic. And when, and I was working there when ChatGPT came out. And what happened was when ChatGPT came out, it became the most popular topic. And so it was an audio app. People would talk to each other on the internet and meet and talk about different topics. And ChatGPT became the most popular topic in every single part of the world. And so I would just join the app, join rooms, ask people how they were using the app, using ChatGPT. And I had so many moments where it's like, oh, photographer, learning about the different settings on their phone, on their camera. Or then you have farmers in my home state in India that are using it to help plan their crop cycle. And then you have people here that are like, I don't like how it rewrites my email. And I was kind of just like, oh, my God, this is a new computer. You know, it's, it's the, it's the first computer that we can talk to.

• 2:58Speaker 01

  It's sort of like the C three PO from Star Wars, except, I mean, you know, Nirmanser, you talk about science fiction. This felt like, like it felt to me that the conversational computer is a hundred years early. Like, I never imagined it would happen in our lifetime. And here it was on our doorstep, already speaks every single language, all the human, well, most of the human languages and all of the programming languages as well. So it's got this like incredible, like general capability. And to think of it only as a work tool is incredible oversimplification. It's, it almost represents the human collective intelligence in a sense. And it's a way for us to access the collective intelligence through natural language by talking to an AI.

• 3:36Speaker 02

  One of the things that I picked up from watching your usage was that you, by prompting a role assignment, you know, whether it's mean VC, skeptical co-founder, emulate a customer, a bunch of other things. But by prompting role assignments and various other forms of kind of meta prompting, that could get you useful things. And obviously, when you combine that with a swarm of agents or a set of agents, that even then becomes more of a, like, part of how we're all deploying a team. So say a little bit about your prompting guidelines, like maybe one that you would hand to beginners and then two or three that you would hand to non beginners.

• 4:18Speaker 01

  For beginners, I think it's mostly start by just prompting heavily, like use voice, transcribe, talk at length about what you're trying to do. And then And maybe assign roles. Yeah, and maybe assign roles. I think you'll find that the model can emulate all these perspectives. Like, you can say, pretend you are a VC and critique my business plan, critique the way I'm running my startup, potentially, if I'm gonna go have a conversation with a VC for capital. Or pretend you are the customer of this product that I'm working on and explore my website. What, do you, do you feel like my website properly, you know, positions our product based on your, your needs as the customer? And so the model gets to pretend to be all these personalities. And so even if you don't have that person sitting next to you,

• 5:03Speaker 01

  you can kind of simulate that perspective. And then the AI, playing that role, will help you understand your problem even in a way that you didn't even consider. Or you might say, I want you to be the most skeptical person of all that you can possibly imagine. And, you know, find 25 different criticisms of my approach to this problem. So I think role, role-based prompting is very, is very powerful, because I think we need to get out of our own perspective. And being able to call on all these other perspectives that the model can emulate is really powerful. I once had a coding agent generate 100,000 unique expert personalities. Turns out, if you create 100,000 unique experts, you kind of cover every single topic, or a huge swath of all of like the topics that humans have.

• 5:43Speaker 01

  Like 100,000 unique experts, covering everything from like parenting to like Legos, to like every single form of art that the models have been trained on. And you get this like very multifaceted like set of like minds that you can tap into. They're not complete minds, but they're perspectives. And then you can say like, find the 10 that are most relevant to my problem, and then have them all answer the question. And they all answer it differently, like that, that different perspective, like an optimist is gonna have a different answer than a pessimist. But then, you know, an oceanographer is gonna have a different perspective than, say, like, an accountant, on almost anything that you present. And so it, it's a very surreal thing. I call that role play. And then I think the

• 6:27Speaker 01

  One of the most powerful prompting techniques, it's in the area of meta prompting, like prompts, like it's the, it's the prompt that helps you find the right prompt. A simple one that I use almost every day is I go to, I go to, I go to a language model and I'll say, here's my problem. I'll describe the problem. And then I'll say, interview me until you have enough context to help me with this problem. Ask clarifying questions and then we're going to begin. And that's really important because I think a lot of people initially you go to AI thinking you know what the answer is. And I think a better way to go to AI is let's describe the problem. And like maybe a set of solutions will emerge. Once the AI kind of collects that context and draws it out of you. The things that maybe you weren't thinking about when you first articulated it.

• 7:10Speaker 01

  And it's really good to, I call it the interview me prompt. Just interview me and then we're going, we're going to begin. And so I do that for any project that I'm starting from scratch. I'll say, interview me and then we will begin. And it might just be a 10 turn back and forth. And I realize, oh, this consideration, I wasn't even thinking about that. And the AI will ask those intelligent follow up questions. Kind of like any good employee isn't just going to start doing the work.

• 7:32Speaker 02

  Yes.

• 7:32Speaker 01

  They ask the clarifying questions upfront and that, and then that brings out a higher quality like problem scope. And then when the AI begins, it becomes much more magical. And you have to kind of, I think a lot of times people just, they need to recognize that maybe the answer that you have in your mind isn't the right answer. And the, the AI can kind of like feed off of your initial suspicion and provide an even better answer when you're in that loop of like iteration. And so I think for a lot of people, it's, it's really just realizing that, uh, being a little bit humble about what our limits as humans are, how many scenarios we can, we can think about and how many considerations we can make. And then using the AI to expand that and parallelize that thinking.

• 8:09Speaker 02

  Part of the thing is the mindset shift of how do you put your ego aside?

• 8:15Speaker 01

  Yes.

• 8:15Speaker 02

  So say a little bit about that because this is actually one of the things that gets in the way of a lot of otherwise smart people's way under delivery of AI.

• 8:23Speaker 01

  Yes. For me, when I, um, when I was interacting with GPT four for the first time. So this was March, uh, March 14th of 2023, GPT four came out, which was the successor to GPT three. And the first big leap after the chat GPT moment was GPT four. And, uh, I was talking to my teammate at Clubhouse. And we were both data scientists, data analysts. And I was like, Olivia, this GPT-4, it writes perfect SQL. It writes perfect analytics code if it understands the schema of the problem that you're working in. If it understands your database organization, it just writes perfect analytics code. And she was like, Parth, this thing aced the interviews for both of our roles. And I was like, wait, what do you mean? Like qualitative, quantitative? And she's like, both. I think it's got a pretty good idea for what we should do as a company, too.

• 9:07Speaker 01

  And I was like, whoa, what does that mean? And, and, and then we went to our manager and we were, we were kind of like thinking about this. We had a small data team, so we were kind of just like, whoa, this language model is clearly an amplification of our own ability to do analysis. And he was basically like, we're not going to hire anyone until we figure out how to use this, and then everyone we hire is going to be using this. Because then we get this like super analytics kind of approach where I'm describing a problem in English and then the AI is executing what I would have done manually by hand. And I had a moment where I asked for, I asked for an analytics query. I thought it was a hard query to write. And it wrote a very elegant solution and I just didn't believe it. And then I looked closely, I was like, oh, that's just better than every version of the solution I've seen before. And it was very humbling.

• 9:52Speaker 01

  And I was like, oh, my God, like, this is, this is definitely better than me at the writing of a SQL query. And then I realized like, okay, I think my job is to aim this. My job isn't to compete on the, like, it's like the Casparov versus Deep Blue moment. But for me, it was like the data analysis. It's like the, or it's like John Henry, the steel man against the steam engine. And I'm thinking, well, I sure don't want to compete on our manual writing of SQL queries anymore. Actually, I would rather be working on the like automated version of analysis where I'm speaking in English to the computer. It starts, it turning my, my questions into computer code that can solve the problems. And so that was a huge shift for me. And I realized a lot of people are a little bit later on that, especially in engineering.

• 10:33Speaker 01

  I see experienced engineers tend to, they tend to be attached to their, their core, their core, their superpower, right? But I think you, looking at AI and realizing eventually it might be better than you at the thing that you were really good at. But then your wisdom of working in that problem space becomes how you expand beyond just the AI or just you.

• 10:51Speaker 02

  And when did you get to that recognition of it being the meta tool?

• 10:56Speaker 01

  I think it was. Probably like three or four months into talking to it for 14 hours a day.

• 11:03Speaker 01

  Realizing it could teach me about programming, realizing it could teach me about music. And then I was, I was like sharing screenshots of my desk and I was seeing that it could actually click around. Like if you allow it to click around the computer and you run it on an API on your computer, you're able to like orchestrate a web browser. You're able to write code in every single language. And I was like, okay, this is like, language is actually the most powerful thing that you could possibly automate. I think that's, that was the realization there that like language touches everything. And then, and then you were always talking about Wittgenstein and he has a quote, which is language is the limit of my world.

• 11:37Speaker 02

  Yep.

• 11:38Speaker 01

  And that was very, that was like, I realized then like my vocabulary, everything I've been exposed to in my life. I could now access intelligence through that vocabulary, through that language.

• 11:47Speaker 02

  So one of the things that in serious part I've learned from you is how we got to voice pilling. Say a little bit about how important it is to actually in fact be using voice. Why that is and what people will learn from that.

• 12:00Speaker 01

  It is probably one of the most powerful prompting techniques there is. If you haven't tried it, it's really like you want to try, you want to go to one of these language models like chat GPT. And I think people get hung up thinking about typing their prompt in a certain way and structuring their prompt a certain way. And I think actually what people should be more concerned with or more focused on is trying to get as much of the ideas out of their head into the model. So it's more about like, you want to say more, you want to be able to get the, you want to describe the problem. And I, I go to the extent of like, I will sit here and I'll ramble for five, 10 minutes to the computer about the problem that I have on my, on my mind. And it turns into like a three page kind of transcript, even though it's kind of like unstructured stream of consciousness. Turns out that is a very high bandwidth way of communicating with AI.

• 12:43Speaker 01

  And I think that some of my best prompts are not the ones that are structured a certain way, but they're the ones where I'm just being extremely effusive. I'm very communicating as much as I possibly can because I'm just rambling at length about the problem. And I find that typing, when we type, we're kind of committing our ideas to a couple of words. And in that process of committing where we're not type, we're not saying as much as we might if we were talking to a friend or we're describing a problem to someone that we wanted helping us with the problem.

• 13:09Speaker 02

  Yeah. And part of that, that use of voice that I learned from you was not just depth of context, but also and breadth and setting the hands. Is when we're typing, we also tend to write like, like precision, like I write a coherent sentence and so forth. Whereas actually, in fact, these are such good, these AIs are such good interpreters, that even if you're like, well, I got a half baked idea here, it actually will guarantee have a more focus that such that you might go, well, that was part of it, but now this is what I really mean.

• 13:41Speaker 01

  Yep.

• 13:41Speaker 02

  And that iterative gameplay, almost like video games.

• 13:45Speaker 01

  Yep.

• 13:45Speaker 02

  Was a real key thing. So there's a relationship between the voice pilling and also like, almost like a video game style interaction.

• 13:53Speaker 01

  Yeah. I, I mean, as a gamer, I think like when you're playing games with your friends, you're not typing to them. You're really just like yelling commands. You're like, oh, I'm going to come here. Here's what we're going to do. And that's, it's faster. It's, it's a high speed. It's, I think any real time coordination, even on a basketball court, people are like, they're yelling at each other. They're like, they're calling out what they're going to do. I think that's, that this is like, the voice is a, is the way to get real time coordination, both between people and also between people and AI. And also, yeah, I see sometimes people will be typing a prompt and then they'll, they'll have a typo and then they'll hit backspace. And I'm like, this thing is really smart. It's okay to have typos. And then if I look at my prompts, all of my prompts are just filled littered with typos because I know it's like, it's so smart that it understands what I'm saying, even though a couple of the letters are in the wrong place.

• 14:37Speaker 02

  Yeah.

• 14:38Speaker 01

  But yeah, same thing with voice, right? It's not about, you don't need to have structured that all the time. I think sometimes if you're going to use a prompt every day, you should think about that prompt. But if it's like a, a single one shot, kind of you're, you're describing a hard problem, it's more important that you describe it at length.

• 14:53Speaker 02

  Yeah.

• 14:54Speaker 01

  Get that context out.

• 14:55Speaker 02

  One of the things also that you do, that I think relatively few people do, is you use multiple of the frontier models, both in parallel, in rotation, in experimentation. How do you choose which models to use? How is that evolving over time? And any? Hacks or heuristics or principles or things that our listeners might be able to kind of apply or kind of remember and take with them.

• 15:21Speaker 01

  Right. So it's a very, I mean, in the beginning, it was just, it felt like it was just OpenAI and ChatGPT. I think that it's easy to get kind of overwhelmed by the options that we have. But the main piece of advice I would say is you want to get good at one state of the art tool in every single category. So one really good language model, one really good image, image model, one really good video model. And then those principles tend to translate over to the competitor products in each category, right? So you get good at ChatGPT, you're also probably going to be good at using Claude and Gemini. And, and any given week, the number one model sometimes is different. So I don't think everyone should necessarily be, you know, trying to stay up to date on that.

• 16:01Speaker 01

  But really, if you have one of the three in terms of Claude, Gemini and ChatGPT, you're really like, like that should be your goals. Be really good at least one of them. And then like every once in a while, you see, try the other ones as well.

• 16:12Speaker 02

  First, a heretical question. Like you said, you know, say bizarrely, someone has not done this at all. What's the model I should start with?

• 16:20Speaker 01

  I would say start with ChatGPT. If you're just getting into language models for the first time, it's probably the best. Like general purpose assistant product, productized version of a language model. And then if you're interested in more technical stuff, I think Claude code and moving into the coding agents is a, is a really good.

• 16:36Speaker 02

  What has been some of your experience in the last six months about like, I prefer ChatGPT for this. I prefer Claude for this, or I prefer Gemini for this, your AI stack.

• 16:47Speaker 01

  Say like my general purpose, like my web browser, I use the ChatGPT Atlas browser. So it's got ChatGPT baked into the web browser and it can control the browser. So you can tell it to click around and you can tell it to book flights for you, book hotels. I'm the kind of person that doesn't book a flight until the last second because I, and it's not that, you know, you know, you're going to go on that trip. But you just don't take the 15, 20 minutes it takes to sit down and book a flight. And I'll just open a tab and these days I just say, ChatGPT, go find me the, the best flight in the evening from LA to, to San Jose. And it'll go find that. And then it's like, go find a hotel and it'll find that. And then all I do is the final booking. So I really like ChatGPT Atlas as taking over this kind of like everyday kind of drudgery kind of work. It's very interesting. It's kind of like a Mechanical Turk AI that just does the menial form filling kind of task.

• 17:31Speaker 02

  How much memory context of you do you have the agent keep in mind like for presumably it's ChatGPT with GPT Atlas?

• 17:42Speaker 02

  To like when you say best hotel, best flight, it knows what your parameters are, for example.

• 17:48Speaker 01

  So I think memory is a very interesting thing that these these language models are beginning to start getting their their like their grasp on. And memory is like, what is that personal context about me, my preferences, my my tendencies, the things that I actually like prefer? That I would want the model to know so that anytime it takes an action, like it's like, oh, Parth likes to sleep in, so maybe don't book him a 6 a.m. flight. Like, that would be an interesting memory point for the the model to take into consideration before making agentic decisions on your behalf, like taking booking a flight, for example. Or, you know, you really only need like, like, I I I think that, like, the better it knows you, the better it can help you with some of these things.

• 18:29Speaker 01

  But memory is very tricky. I think it's largely unsolved. I think ChatGPT has more of my memories. But I also noticed that sometimes I'm like, I don't, I actually prefer talking to a coding agent that knows nothing about me personally. And I and I and I because I like to sometimes have a fresh slate with these models where they're not assuming anything about my my preferences or my tendencies. So I think it goes both ways. The personal co-pilot, you kind of do want it to have some sense of memory. But then, like, your automation tools, maybe they don't need the same level of personal life kind of understanding. And then my everyday primary co-pilot is ChatGPT.

• 19:08Speaker 01

  Obviously, because it's got a great mobile app, you can point your phone at things and talk to it about the real world, use it to help you solve problems every day. Like, even just like, oh, how should I organize my my like apartment? Like, I obviously should buy some containers to organize my my my closet. It's very good for like the in-person, real-world kind of AI and really good for research. ChatGPT Pro Mode is the best research tool that I've ever seen, and it's it continues to be the case. And then I would say after ChatGPT, it's I've got my coding agents. So I usually have three coding agents assigned to almost anything that I care about in my life. Just like this. Yeah, I have a Claude, a Codex and a Gemini. And they're just attacking three. And this is just one project.

• 19:49Speaker 01

  I have like, you know, seven, eight other projects where I'm just spawning more, more agents in different directions at the same time. So I would say the coding agents are more like my ambient fleet, where anything I care about has one to three agents on. Any project that we're working on, Read AI, some of these creative projects, or when we're building something new, the first thing I do is I create a folder and I put Claude, OpenAI's Codex and Google's Gemini into that project. And I just send them in three different directions on that project in an empty folder. And I kind of transcribe to them and I tell them what I want them to do. And then they kind of just work on that in the background. And, and then I spin up another project and I have three more on that project. And so I'm at this point now where it's like anytime I have a new idea,

• 20:32Speaker 01

  my instinct is to put three agents on it and have them make some progress before I come back to it.

• 20:38Speaker 02

  What do you think is the maximum number of projects you've spun up with your trio of agents?

• 20:43Speaker 01

  This fleet, I've gotten up to like 17 projects where they have on average two to three agents in each one. I think this is just a current constraint. And it's something, it took me like three months. The last three months, I kind of designed my workspace to allow for this kind of context switching. Because then it's, it's like, when, especially when, if you look at the frontier models now, GPT 5.2 and OPUS 4.5, you can set them up. If you tell them, if you give them a good approach to planning, and you say, make sure you write down the plan and periodically update your status in the plan, you can say, go work on this for today. And it will continue to work in a loop for a whole day, even longer than that. And then people are like, oh, how, like, why would you want multiple agents? And I was like, because when you tell someone to work on something,

• 21:27Speaker 01

  like, you're not going to just walk away from the computer and like, go to the beach. You're, you're like, no, actually, I want to fire up another one. You know, like, then, then the justification for having kind of like a small fleet, a couple of different directions going at the same time makes, makes perfect sense to me. And I think that as we get better at like the user interface constraints and the context switching, I think the code review and how many of these can you manage is really a question. I think a lot of people are still in the single co-pilot phase. And I think right now is probably the time to move into the, how many of these can you orchestrate at the same time across a range of different projects?

• 22:03Speaker 02

  Like the trio of agents, awesome. We'll get to what people should be willing with one agent in a second.

• 22:08Speaker 01

  Yep.

• 22:09Speaker 02

  What's the funniest thing or the funniest thing that comes to mind about what's gone wrong with one of your trio of agents projects?

• 22:17Speaker 01

  Yeah, so when we first met like two years ago, I was thinking about this problem, an earlier version of this problem of like, can I put two chatbots in a room and then give an objective and then like, can they make progress? And then walk away from my computer. The first time I did that, I realized that they, you know, they would work on a problem and then they would not know when to end the conversation. And so they would just say thank you to each other in an endless loop. And I came back and I spent like a couple hundred dollars on the word thank you. And I was like, oh my God, what are we doing here? Do I need to create a manager to say, end the conversation? Which is what I did, like, it felt like a naive thing, but I was like, makes sense to have a third person in the room that just ends the meeting, right? And then, and so, but that kind of clued me into this idea that maybe the coordination

• 23:00Speaker 01

  across multiple chatbots with their own context windows is like largely kind of unsolved territory. And now we're in that same phase, we're in the next version of that same problem, which is they're not just chatbots, but now they can take actions, they can work on projects. And I tried it again, right? I said, okay, what if I had, gave them the ability to talk to each other and, or like send messages to each other, right? They can send messages to each other, or they can see where each other are in a project. And it was experimental, it was basically allowed three different coding agents to DM each other while they worked. And I realized, one, they kind of missed timing a lot. So like, they'll be working, but they, they'll get a message and then they'll reply to the message. By that time, the other agents already like halfway through the problem. So there's something about like timing.

• 23:42Speaker 01

  And I also realized that it opens interesting questions as to like permissions. Because you'll have an agent and it'll be working on a problem and it might be like, oh, user, I need some, I need you to approve me using this tool. And me being a human, I can give that approval. But then if it starts asking the other agents for approval, it's like, oh, hey, Codex, I need to use this analytics tool, what do you think? And then Codex is very willing to just approve that access. And I was like, okay, maybe this breaks our definition of a sandbox if they can just ask each other to permission themselves.

• 24:13Speaker 02

  Is it okay if I erase the hard drive? Yes, absolutely.

• 24:16Speaker 01

  Yeah, exactly. That's the, that's the risk there, right? So, so then I was like, okay, if we're gonna do that kind of experiment, we should be sandboxing it, we should run it on a machine where we don't care if we lose everything, right? Like a virtual machine. With a Docker container. But it is interesting because I think we're going to get there where like I want them to be able. The only like how I deal with that now is I just send them in different directions. I say like, you're going to research, you look for bugs, and then you help me with like the blog on my website. And then I know like their work doesn't overlap. And so there's less likely to have, we're not going to have this like collision of like different workers. And I'm sure that something similar to what GitHub did for humans is going to be, there's going to be something, some similar kind of solution for coordinating multiple agents working together on the same project.

• 24:57Speaker 01

  Then when I want to deploy software to the web, I want to make an app and then share with people, I use Replit. So Replit is another coding agent. But and and these, these three agents will work with the Replit agent on a project. Like my website is built and hosted in Replit. And these Codex and Cloud Code have helped with the website, but it is, it is largely Replit's agent has built the website. And so that's really good because if you want to deploy software, there's no easier way than Replit. And then for image models, I really like Nano Banana from, from, from Google. Nano Banana Pro from Google is the most powerful image model. And it's good for, it's not just about generating cool images of like surreal things.

• 25:40Speaker 01

  But it's also very good at building, like designing infographics that are extremely coherent. And Ethan Malik, he thinks that, he thinks that Nano Banana is kind of like a successor to PowerPoint in the, in the sense that it can create this rich visuals with coherent text and layout. I think, I think it's some combination of code and, and generative images like Nano Banana is probably the evolution of presentation tooling. I like Nano Banana. I think other image models I like Flux, Flux from the Black Forest Labs team. It's, it's kind of an open source model. I also like, of course, Mid Journey is best in class in its own category. For video models, I really like Sora and VO3 from Google. So Sora from OpenAI and VO3 from Google. These are the most powerful video models I've seen.

• 26:26Speaker 01

  And so I use them for animation pipelines. So I'll take a coding agent and I'll give it an image model. And then I'll give it a video model and I say, help me animate this world. And it'll start creating scenes and characters and animating them. The intersection of coding agents and all these other creative tooling is also a very interesting. It's a new form of animation, new form of like world building and storytelling.

• 26:46Speaker 02

  Some of our folks are probably listening to your description and thinking, oh my God, sci fi, like, you know, William Gibson, the future's already here, just unevenly distributed. But like if someone said, okay, I'm gonna start using an agent.

• 26:59Speaker 01

  Yeah.

• 26:59Speaker 02

  What would you go, okay, start using an agent thus?

• 27:04Speaker 01

  I would say, start with ChatGPT. And maybe I would say, start with like the ChatGPT Atlas browser. If I type slash agent mode, now we're in agent mode. And so ChatGPT is a chatbot, but I can say, let's go to the tech meme front page and look at some of the headlines. And then maybe pick an article and then open it up. I've transcribed my prompt and I'm gonna send this message. And now ChatGPT is gonna take control over the browser and then navigate to the website and explore the front page. Looks like there's an OpenAI article right there. And you can see on the right side, it's thinking about how to browse the website. And it's clicking on the first, it's probably gonna click on the first article. It's reading this article. Let's surf, let's surf Wikipedia and I wanna learn about language models. So let's go explore Wikipedia.

• 27:45Speaker 02

  And by the way, for those people who don't have the Parth command line, the agent mode's also available on the button.

• 27:51Speaker 01

  Yeah, there is a button.

• 27:53Speaker 02

  Just, you know, it's all cool, but it's just, you know, making sure.

• 27:56Speaker 01

  I've gotten so, I've gotten so hot key oriented that I'm like, I won't even use the trackpad. And so right now, we're watching ChatGPT use a web browser. And I think this is like a pretty, pretty, I mean, I think if you're gonna, if you're just getting into what is an agent? And you've maybe you've talked to ChatGPT or a language model before. This is a version of an agent that can take actions, right? Without me clicking around, it took us to Wikipedia. You could tell it to book a flight, you could tell it to, to research a topic. And you can fire off more, you can open up more tabs and then there have more agent mode queries running. And on the side, it's explaining, we can talk to the, we can talk to ChatGPT about the contents. So I think that ChatGPT as an agent is probably the best everyday agent. There's so many more capabilities, but I think for research,

• 28:39Speaker 01

  it's probably one of the best. And also just for personal everyday kind of exploring the web. Everything we were, we were using the web browser for is now you have a very intelligent language model that can help you explore pretty much any topic, learn anything, teach yourself anything. And I think that's the, the most powerful thing you can do with AI is having it teach you about how the world works.

• 29:00Speaker 02

  So we've covered some of the entry points. Now, what is it, one of the things that, as you know, one of the ways that I describe you off the matrix is not only have you taken the red pill, but you're bathing in the red pill. And as a question that's kind of in the

• 29:15Speaker 01

  The Morpheus.

• 29:16Speaker 02

  Yes, the Morpheus then. What does it, you know, look like for an individual to cross the line from, you know, kind of asking questions and using ChatGPT as a search, you know, engine or kind of like a, give me my, my research Wikipedia answer, et cetera, but to building agentic systems, automations around themselves. And in particular, share an example from what you do.

• 29:40Speaker 01

  So I think like, we talked about ChatGPT, that's a great like intro to language models and agents. I think that the, if you want to go one step further, I think you want, there are limitations to this chat experience in a web browser where you, you actually, the, the real power of the language model is unlocked when you give it a computer and you allow it to kind of use a computer with you, use your own computer and like working with files on your computer. And for me, one of the, the first things I realized I needed, I was like, I should have a personal website. I should start talking about these things. I thought, well, AI is going to help me build my website. And I've never done this before. It's like, I need to build a, I want to build my first website from scratch. And so I went to, I went to AI and I said, let's build a website. And now I think it's

• 30:23Speaker 01

  like, these coding agents that built first version of my website, now they run my website. And so I'll just show you. So if we look at my screen right now, we see three panes. And this is kind of in the, the space of like the Morpheus kind of thing. So on the first pane on the left, I'm going to launch Claude. Claude, and this is Claude code. So this is Anthropic's Claude, but running on the cloud, but working on my computer. In the middle one, I'm going to launch Codex. Codex from OpenAI and on the one on the right, I'm going to launch Gemini. And all three of these agents, so we see Claude, Codex and Gemini. All three of them are actually working in the folder, which has my website code. So I'm going to fire off three different tasks. Gemini has got the longest context window.

• 31:04Speaker 01

  So I'll say Gemini, read every single blog post that I've written and suggest the next three topics we should cover to help people who are getting into working with AI agents and language models, discover this kind of value that we've found over the last couple of years. So transcribe the prompt, send. Now Gemini is going to read all the blog posts that I have.

• 31:24Speaker 01

  We'll go to Codex. Codex, can you please pull all of the website traffic analytics and suggest improvements and next steps for improving the performance of the website? Both from a performance on like maybe engagement on the website as well as maybe on the content side of things. And then we're going to have Claude. Claude, I need you to open my website and then we should take a look at how it looks like on a mobile experience. And then I want you to browse it as if you are someone visiting my website for the first time. Someone that wants to learn about AI, wants to learn about working with coding agents. Pretend you are that person on their phone, exploring my website. And let's give me feedback on the website to improve the experience.

• 32:03Speaker 02

  And here we've kind of demonstrated three different agents in the, not working the same thing, but kind of giving different, same file, but different tasks.

• 32:12Speaker 01

  Different objectives.

• 32:12Speaker 02

  Different objectives, so they're not combining. And then, you know, a little bit of what's implicit is which ones do you think will be, you know, a little better at each task?

• 32:21Speaker 01

  Exactly. And if we look at it in the middle, we have Codex is pulling analytics numbers across the website. It has access to the analytics.

• 32:27Speaker 02

  Yeah.

• 32:28Speaker 01

  So me being a data analyst, the first thing I figured out was like, it's really good at analytics. Now we have Claude has pulled up my website in Google Chrome and it should, the next thing it'll do, resize it for mobile. And now it's going to, and you can see how it's thinking, I'll open your website. Let me resize it. And next thing it's going to, it's going to explore the website like it's a user. And we also have Gemini behind this that's just reading every single blog post. Look, it's giving us feedback, nice hero section, good content cards. Let me continue scrolling. Meanwhile, we have Codex that's running analytics. So here it's reading a blog post I wrote about Claude code. Yeah. So this is, I think the building a personal website using many multiple agents is very obviously useful for like most solopreneurs. It's a single website. So it's a single person made the website. Like I made it with AI.

• 33:11Speaker 01

  I wouldn't even know how to do this without AI. Let's be honest. Like you go back three years and it's like, okay, I'm going to learn every single programming language and then figure out how to stitch it all together. It would take months. Usually you have to hire people to do that. And then the quality is also higher than I could ever imagine because the AI is so good. And I can also aim it at things and say, I like this website. Let's emulate that kind of.

• 33:33Speaker 02

  So hopefully one of the things, you know, our various listeners have picked up here is the scope of, like, like you're just throwing darts where you have a complete set of things in each of these different directions. What's, who are some of the sources, whether it's podcasts, social media feeds, et cetera, of people that you pay attention to, to learn more about prompting?

• 33:57Speaker 01

  Oh, for prompting, I think this is Dexter Horthy. He, great AI engineer. He, I met him earlier this year. We were talking, we were, we met in a group. It was kind of like a Claude Code anonymous group. It was the, the requirement to get in the group was to be addicted to Claude Code. And everyone was kind of just like, we were sharing how much we were using it and how we were using it. There's all these different techniques for like, running many of these at the same time. And so Dexter, he, like, we had some very interesting dialogue on, on like how to orchestrate many agents. But then he actually kind of really expanded on the idea of context engineering,

• 34:37Speaker 01

  where there's prompt engineering, which is like, maybe came into the play like in the ChatGPT 2023 phase. But now context engineering is like, actually, I think the better way to think about it is like, what are the various techniques we have for bringing the right context into the model and making sure it doesn't have the wrong context? So we're not wasting its cognitive bandwidth on the wrong context. And how do we, like, our job as, as AI engineers is to think about the context window as a, as a canvas. And we're like filling the canvas with the most relevant context, whether that's images, whether that's code examples, whether that's like, tools that it can use without cluttering its mind and then giving it an objective and hoping that it is the right mix of information that will allow the model to do the right job.

• 35:22Speaker 01

  And so he thinks a lot about context engineering and I've learned a lot from the way he thinks about it. Even in how we use coding agents and like, you know, coding agents, you can't give one of these coding agents unlimited tools. Like not yet, right? They don't have unlimited cognitive bandwidth. But then there are ways to give them tools where they can use a broad set of tools without having to memorize every single one upfront. Where I think the term uses a progressive disclosure. So if you give it a, if you give it, create a tool and the tool has a help guide on how to use the tool. Then you don't need to explain the tool upfront to the agent. The agent just needs to read the guide. And only when it needs to use that tool.

• 36:02Speaker 01

  So he kind of helped me think about like, okay, how do we, how do we design tools for our coding agents so that they're not constantly getting overwhelmed by all the things we want them to do, but they do a really good job at the few things we want them to do. So in this case, the Claude agent has access to a web browser and has like access to some of my personal knowledge. And so it's able to like use the web browser, but the other agents aren't using the web browser like that. And so they're more free to think about the content and the strategy. And on the creative side of things, I think there's Don Allen. He's, I've known him since high school. He's one of the, he's one of the most prolific AI creators. Someone who's able to weave like these, wield these like creative models, the image models, the image models, the video models.

• 36:42Speaker 01

  Dave Clark, also extremely good at visual storytelling. I think, I put them in, Nem Perez. I'd say I put these three in the category of the new Hollywood where it's like, what if the studio is in your pocket? A couple of these models is helping you tell your story. And so they're very good at like animating short stories and creating like trailers. And now they have, they have their own studios that they're working on and trying to like discover the new workflows of the entertainment industry and entertainment space. I think on the, if I think about who's the ultimate like creator entrepreneur, you talk about like treat your, treat your life, like your, your life is a startup, right? Like the startup of you. I think top of that list for me is Cat GPT.

• 37:23Speaker 01

  She is like a solopreneur creator. She's built a large audience through talking about AI and playing with the tools. Kind of like we do very publicly, but also making it make sense to almost anyone. So if you follow Cat, you're just going to learn a lot about AI in a very non judgmental, everyday, useful kind of way. And she's leaned into the more technical side of things. She's picked up vibe coding and she's starting to use those capabilities to launch businesses and small teams working on like highly lucrative projects more efficiently than ever before because now you have the like amplified creator entrepreneur that's coming online. So she has the media piece, extremely good at video, extremely good at media, and extremely good at that distribution side of things. Built an audience, became well-known, and also is now like building products for that audience. I think that's a very exciting person to watch.

• 38:08Speaker 01

  So I think of all of these people as AI-native people. And like, these are the people that I'm constantly kind of following, trying to understand where we are, what can be done. Of course, Andre Karpathy, who's like, I mean, I think he's, he's kind of like that, that person who, when he speaks, every time it's like, oh, what does he think about coding agents? He's like, ah, they're kind of slop. It's like, huh, maybe they are slop. And then you start thinking like, yeah, it's magical from my perspective. But then you take an expert and you think about like, he's thinking about the jaggedness of intelligence and like how, you know, it's so good at these things and entirely like useless in other lenses, right? And thinking about that more on a, on a very deep level of where does that, where do language models go, where are their limits?

• 38:51Speaker 01

  So I think Andre Karpathy is probably one of the best people to follow for AI researchers.

• 38:55Speaker 02

  This is, I think, the path that we're all on, whether or not we know or not, is how do we become AI-native? So what is, like, what should an individual consider doing to, you know, start making their life more magical? We've got a bunch of different prompt ideas, but a bunch of things. But like, what are the things that, you know, you who, you know, basically ask yourself every single thing you trip across is, can I have AI amplify or do that? What would you say for individuals to kind of start making, like, to seriously engage in doing to, to experiment with making their life magical with AI?

• 39:36Speaker 01

  Yeah. I think about this a lot. For me... I would say, I would say that the main thing is that you should apply AI to something that you're intrinsically motivated by, like your passions, your interests. I think there's a, there's like a default kind of approach, which is like, I gotta use this for my job. I gotta become more productive. And that's fine. But I think what's more interesting is using it to expand your sense of self. Like whoever you were before these tools came online, I promise you, like, you're much more than that. Once you start interfacing with these tools, you start expressing yourself through these tools, right? Now, I think of myself as a visual storyteller. I think of myself as like animating, like animating worlds and creating worlds, right? Even though I was a data analyst, maybe just three years

• 40:19Speaker 01

  ago, now I'm also an engineer. I'm like a vibe coder, right? Or what you might call it. And I think it's like the expansion of the sense of self is, it's like you could think of it as like a replacing of what you were. But I think the other end of it is like an expansion of your sense of self. And if you aim this at your passions and your interests, so in my case, like music, games, visual storytelling, I think that allows me, then it's like, no one's going to tell you to do it. You're going to see the magic. You're going to, you're going to discover like the, the upside because it's something that you didn't think you had. Like, I think of it as like, I get to live all these other lifetimes. I get to be all these other things that I kind of like sidelined in favor of my career, but now I'm expanding back into them, coming

• 41:01Speaker 01

  back into them in a different angle, right? So, and, and it's an intersection of so many of my interests of both technology and creative and computers. And, and I think that a lot of people will experience something similar, which is the expanded sense of self through this kind of like technology.

• 41:17Speaker 02

  I think that people don't realize that with AI, they need to re-expand their imaginations for a sense of self, for sense of capability.

• 41:26Speaker 01

  Yeah. And you'll be surprised at how much more ambitious you become when you see what you can do. It's not, you're not going to just generate an image and like call it a day. You're gonna be like, whoa, actually, let's create a world around this, maybe a story around this. And it becomes a bigger kind of ambitious pursuit.

• 41:40Speaker 02

  Possible is produced by Palette Media. It's hosted by Ari Finger and me, Reid Hoffman. Our showrunner is Sean Young. Possible is produced by Tanasi Delos, Katie Sanders, Spencer Strasmore, Imo Zoo, Trent Barboza, and Tefazwa Nirmurundwe.

• 41:56Speaker 00

  Special thanks to Surya, Yala Monchili, Sayida Sabieva, Ian Alice, Greg Beato, Parth Patil, and Ben Ralas.