Loading summary
Transcript1 lines
- [00:00]
A
Today, on this AI Operators Bonus episode of the AI Daily Brief, we're talking about how to learn AI with AI. The AI Daily Brief is a daily podcast and video about the most important news and discussions in AI. All right friends, we are back with another unplanned AI Operators Bonus episode. For those of you who are new around here, these Operator Bonus episodes are not anywhere near our normal format. They're not about the news, they're not about a discourse, they're not about a big idea necessarily. They are instead much more practical and specifically for people who are trying to figure out how to use AI. I toyed with the idea of actually spinning out a separate AI Operators Podcast this year and decided, at least for now, to drop these bonus episodes in the feed sometimes when it made sense. And so I'm always interested in hearing your feedback on whether these things are valuable, whether you want more of them, whether you think they should be on their own feed or anything else. And what we're trying to do here is talk about how to learn AI. Specifically, we're talking about how to learn AI with AI. But the genesis for this is that I think that the way that learning is going to happen has fundamentally shifted. Instead of a paradigm of instructor led tutorials, explainer videos, step by step guides, basically that entire former paradigm of education and particularly online education, instead, now everything is going to be effectively the equivalent of pair learning with an AI build. Partner AI, in other words, is going to be your companion for using AI to learn. And it turns out there's a lot to figure out about how to do that. Well, now I want to give a little bit of specific context and why this is coming up right now. First and most important is that just after OpenAI announced 5.3, Codex President Greg Brockman talked about how the company was endeavoring to work in a fundamentally different way. He tweeted by March 31 we're aiming that for any technical task, the tool of first resort for humans is interacting with an agent rather than using an editor or terminal. In other words, agent first work by March 31st. Well, you might have noticed that has kind of a ring to it, and something I've been thinking about a lot recently anyways, is how to give people better resources for self directed learning around what I see as this shifted paradigm of AI. Already we weren't doing such a good job of helping people learn how to use AI, and that was before this code AGI moment that we've experienced over the last couple of months. Now everything is shifting once again. And while the ceiling of what you can achieve has heightened dramatically, so too has the difficulty of using the tools to get there. Now I had already wanted to expand what we built for the AIDB New Year's resolution program into a broader free self directed learning platform, but this just sped up the timeline. Okay, so we've got this idea of agent first work by March 31st. But the other catalyst for this actually came from a discussion on a post by Tribe CEO Jacqueline Rice Nelson. Now to be clear, Jacqueline is great. Tribe does awesome work and the broader point of her post, which is that the UI and the products around agents need to improve dramatically for them to be widely adopted, especially in a work or enterprise setting. I absolutely agree with her post was about how a bunch of her non technical team members and herself had used Claude Cowork to do things that were impossible for them just a few months ago. But when they actually dug in it was quite difficult and in fact many of the team had actually paired with engineers for hours to get the output that they eventually got. The line that got me was this. What Cowork really shows us is what many of us already knew. Claude code is incredible. We're seeing a glimpse of the future where these capabilities will be available for everyone. But the future isn't here quite yet. The part that got me to bristle was this part the capabilities will be available for everyone. My contention is that for anyone who is high agency enough to take the time to work through these challenges, the capabilities are available right now. What's more, the people who take the time to take advantage of these capabilities being available right now, difficult though they may be, are going to be the people who shape the next generation of work in the economy. And in my mind, the foundational mindset shift for being able to take advantage of those new capabilities is to stop looking for tutorials or videos or explainers and fully embrace the idea of AI itself as your learning and build partner. Now I've been living fully in this reality for a couple of months now. I have dozens of live projects on lovable a bunch of things that I'm building in Claude Code seven agents that are actively interacting with me via openclaw that I built over the past week and I don't know how to code. I am completely and utterly non technical. What I have is Claude to help me work through things step by step, figure them out and persevere even through challenges that might otherwise have stopped me. But I realized that how to work with an AI learning partner like that is not Self evident. And so as I was working on these projects today, I actually asked Claude to extract some of the lessons that we had figured out as I had worked with it over the past couple of months. And the rest of this episode is about those tips. So we, the royal we, me and Claude have broken it into two categories. The first is mindset shifts, and the second is specific tactics. I'm going to go through them kind of fast, but hopefully this provides a way to think about how to dive into using Claude or ChatGPT or Gemini or whatever your preferred LLM is as your learning and build partner. Okay, so mindset tips first. Number one, you gotta start with the vision, not the task. The watchword for AI in 2026 is of course, context. And when it comes to building like this, the context that the AI needs is the big idea of what you're trying to achieve. That means instead of saying, help me build a learning platform to help people launch their first agents, instead you start with your goals and your perception of what does or doesn't exist out there and what the challenges are. It might feel slow, but I guarantee it's going to save time on the other end and get your AI partner way closer to what you're trying to actually achieve than just trying to describe the outcome alone. Now, in some cases you might even not know exactly what you're trying to achieve or not fully. Which brings us to tip two, which is thinking out loud even when it's messy. One of the things that I realized earlier today is that I was actually building two things at once. One was a set of self directed skills projects that people could combine in whatever way that made sense. The second was a library of agent starter prompts that people could just download. I think the exact line to Claude was, okay, not to be insane, but am I building two things at once? Your AI partner has the capability to handle that sort of messiness. It doesn't need perfectly formed thoughts to be useful. In fact, much of its utility is in helping you think through half formed thoughts. Number three, and this one could be hard to get used to for some, you gotta push back hard. And often AI doesn't have feelings in the way that your employees or colleagues do. To the extent that it wants anything, it wants to help you achieve whatever it is that you're setting out to do. And one of the things that anyone who's used AI knows is that it says everything pretty confidently, which means you have to push back. Now, an inverse of this, which is a little bit better with current models, but which is still a little bit of a challenge is you also want AI to push back on you. And sometimes that involves explicitly saying, I'm not sure about this, I want you to critique it from first principles, or something like that. The point is that the conversation can't be the AI just accepting your ideas as good or you accepting the AI's ideas as good as you gotta push back on each other to make progress. Number four. And honestly, this probably could have gone with Think out loud is sort of a subset of messy thinking out loud, which is dump first, organize later. Once again, you don't need to have everything perfectly structured. And in fact, a lot of what AI is good at is taking your messy, disorganized and unstructured thoughts and structuring it in ways that can help you make progress. Number five, AI partner as mirror. Sometimes you need the AI to generate a net new idea. A lot of times you need to speak an idea to it and have it play it back for you to make sure it makes sense. And the lesson here is that you know more than you think you do. You don't have to rely on the AI for all the new ideas. A lot of its job is to help you work through your own. An example from our building earlier today, we were trying to talk through what the categories would be for the agents on the Agent Bench portal, where you can download this starter template to start working through building your own agents. And after the AI gave me a set of categories that it thought made sense, I fed it back the seven that I had built with openclaw this week to see how they would fit together. It ended up revealing a couple of gaps in the framework that I didn't consciously catch, but which something else that I had built actually revealed. Number six, I would summarize as get existential every once in a while, especially the deeper into the weeds you go, it's really valuable to zoom all the way out and reground yourself in what you're actually trying to build. I can't even tell you how many different versions of AIDB training have existed in my head. And even as I've been designing this project, it's shifted. It is very, very easy to get lost in the sauce and knee deep in the weeds. And to the extent that you can pull yourself out every once in a while, it's going to help you and your AI build partner reground yourself in what you're actually trying to accomplish. Number seven. This is another one that I think is sneakily difficult for people because it's not how we're used to thinking about things. I think a lot of the first way that people used AI was they drafted stuff and then they had the AI comment. I think increasingly we're shifting in the other direction where the flow that makes the most sense is to let the AI draft and then to react. Take advantage of that near infinite output capacity to go wide first. Today, as I was thinking through what skills projects I would want to have to start off, I asked the AI to write a slew of initial titles based on our categories, and it came back with 110 in about 30 seconds. I was able to very quickly spot that there were certain patterns and trends inside those that weren't really going to work, and we went on from there. A last really important mindset shift is to know when to stop a threat and move on. The AI will walk with you down any rabbit hole as far as you want to go, and pretty much the only time that you hear from an AI something like, hey, do you think we should move on? Is when it's coming to the end of its context window. And that's its equivalent of telling you that it's tired. In general, it will happily go as deep as you want on just about anything. Which means it's your job to manage the session and decide what matters now versus what matters later. You also are allowed to temporarily diverge and then come back. I had a tangent that I knew was a tangent that I just wanted to think through in the form of a single question. And then after I got the answer to that question, I said, let's willfully ignore that for now. We've got enough things to think through. Remember, at the end of the day, you are the project manager of the conversation. Your AI partner is going to follow you wherever you lead. Now let's move from the mindset shifts in thinking about how to interact with your AI learning building partner, and shift instead to some tactics. The first and maybe singularly most useful thing in anything that I'll say today is handoff documents. AI conversations have limits. Long sessions accumulate a lot of shared understanding that exists only in that current conversation. If you don't capture it, you start from zero next time. Yes, all of the platforms have some version of memory, but it's very nascent, it's very unreliable, and it requires you. At least at this moment. This is the type of thing that in three months when someone's listening to this could be entirely irrelevant. But at least in this moment, you have to explicitly capture the context before you move to a new conversation. What you will find is that when you start to get into a complex project, it will not take you as long as you think to get to the end of the context window before you do, or especially as it's starting to happen, as you start to see those telltale signs where the AI forgets a detail or starts to get lazy or whatever it is, it just feels like you've been talking to it for a long time. The little scroll bar on the side has gotten little and tiny because there's so much there. Ask it to write a handoff document that captures the key themes, the decisions, the open questions, and the current state of the project. Whatever type of project it is, you have to kind of treat every working session like a shift handoff. You document what was decided and in many cases the process that got you there, because that's really important context too, as well as what's still open and what comes next to additionally support that persistent context. Use whatever your LLMs version of a project setup you can so for example, you saw here that I'm using CLAUDE projects. I have projects for major buckets of work. Each of them has their own set of conversations as well as their own set of files. And you can see this is the OpenClaw agent project that a lot of the files are handoff plans, setup plans, architectural plans. Basically the additional context that future instances of that LLM are going to need to continue to help me. Without losing too much in translation, all of the big LLMs have some version of this at this point, so whatever you're using, put it into whatever that version of a project is. This next one is kind of obvious, but for the sake of completeness, don't forget that all these models, they can look at stuff in the form of screenshots. And while screenshots are obviously useful for if you're working on anything visual like a design or a layout, you can also screenshot an error message, a snippet of code. In short, remember that your AI Learn build partner can read stuff in an image as easily as it can when you copy paste it in. Especially as I have been setting up openclaw, my conversations with my CLAUDE partner are basically nothing but screenshots of the terminal, where I'm effectively saying what the heck does this even mean? Related to that, get out of the habit of paraphrasing just copy and paste stuff when you're talking about error messages, parts of a UI you don't like, a code snippet, a paragraph from a document. Do not paraphrase it, don't summarize it, Especially if it's a technical problem, your AI partner can work with exact content far better than it can with your memory of it. As insane as this sounds, copy paste is a core skill of learning to learn with AI. Next up, One of the things that you will find as you dig in, especially as you get more complex, is that you're going to be bouncing around between a lot of different AIs. You've got your AI Build Learn partner who's helping you coordinate the whole thing. You might have a different LLM that's helping you with some other parts. For example, if you're using Claude, it doesn't have image generation, so you might be using Gemini's Nano Banana Pro. And then of course, if you're using a build tool like Claude Code or Lovable or Replit or anything else like that, you're going to be moving context and content around between a lot of different AIs. Use your AI partner to write the prompts for your other AI partners. Get in the habit of explaining to your AI partner what you want one of the other AIs to do, and have it write the spec or the prompt or whatever it is that's needed to communicate that not only is it going to be more precise, but it's going to be a lot faster to have it do the writing. Now, the one caveat proviso addendum to this is that as you do a lot of this, it can get very easy to just assume that what your AI Learn partner has written is correct and fully representative of what you're trying to communicate. Take the time to click the file that it wrote, scroll through it, and make sure that it accurately says what you want it to. You would not believe the number of times, for example, this week that it tried to switch the models that I was using on me when initially at least, I just wanted everything in Opus. Now it probably knew better, and I probably could have been saving money using Sonnet 4.5, but that's neither here nor there. Overall, the point is, use your AI partner to write the prompts for your other AI partners. One more tactic that's still in the framework of the importance of context is to avoid the instinct to start over. Sometimes, when something isn't working, it feels like the best idea would be to start a new conversation. And certainly in some cases that's right. But when you do that, remember that you're throwing away a lot of accumulated context, not just in terms of decisions, but things you've thought through and rejected ways of looking at the problem that haven't worked out that can be really valuable. So you really have to have a very high burden to just start from scratch. Lastly, and I cannot recommend this enough, while there are some very specific times that you want hyper precision and you might want to type something out, you will move so much faster if you are talking literally with your words to the AI instead of just typing. Now unfortunately you probably know that the native text to speech in your devices isn't very good. Luckily for all of us there are an increasing number of tools that are much better. I use Whisper Flow and while it's not perfect, I literally would be moving about a third as fast if I didn't have it. The single biggest speed pickup that I can offer you probably is making the switch from typing to talking. So that's the idea. In this new agent age, the way that we learned before is just out. There really isn't a better path than just diving in. And while that may have always been the case that practice beats theory, the difference now is that you have this unbelievably powerful partner in a way we never had before. All of the things that might have made you feel nervous about just starting the volume on those things is turned way, way down because you can simply have AI as your partner for that learning process. So that's going to do it for this bonus Builders episode. Hopefully this was useful and if it isn't yet, maybe flag it and come back when it is. Appreciate you listening or watching as always and until next time, peace.