Using LLMs To Expand Your Working Vocabulary - podcast episode cover

Using LLMs To Expand Your Working Vocabulary

Jun 25, 202513 minEp. 1256
--:--
--:--
Download Metacast podcast app
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more

Summary

Jonathan Cutrell explores vocabulary as a fundamental skill for career growth, resilience, and clarity, defining it broadly to include mental models, self-understanding, diagrams, and programming paradigms. He explains how this conceptual vocabulary provides access to nuanced thinking and helps in navigating career transitions and disruptions. The episode highlights Large Language Models (LLMs) as powerful tools to refine and expand this skill, enabling exploration of new subjects and identification of leverage points. Listeners are encouraged to focus on understanding the "why" and "when" of concepts, not just "how," for deeper insights.

Episode description

This episode explores the fundamental mindset of building your vocabulary, extending beyond literal words to conceptual understanding and mental models, and how Large Language Models (LLMs) can be a powerful tool for expanding and refining this crucial skill for career growth, clarity, and navigating disruptions.

  • Uncover why building your vocabulary is a fundamental skill that can help you navigate career transitions, disruptions (such as those caused by AI), and changes in roles.
  • Understand that "vocabulary" goes beyond literal words to include mental models, understanding your own self, specific diagrams (like causal loop diagrams or C4 diagrams), and programming paradigms or design patterns. This conceptual vocabulary provides access to nuanced and powerful ways of thinking.
  • Learn how LLMs can be incredibly useful for refining and expanding your conceptual vocabulary, allowing you to explore new subjects, understand systems, and identify leverage points. They can help you understand the connotations, origins, and applications of concepts, as well as how they piece together with adjacent ideas.
  • Discover why starting with fundamental primitives like inputs, outputs, flows, and system types can help you develop vocabulary, and how LLMs can suggest widely used tools or visualisations based on these primitives (e.g., a scatter plot for XY data).
  • Explore why focusing on understanding the "why" and "when" of using a concept or tool is a much higher leverage skill than merely knowing "how" to use it, enabling you to piece together different vocabulary pieces for deeper insights.
📮 Ask a Question

If you enjoyed this episode and would like me to discuss a question that you have on the show, drop it over at: developertea.com.

📮 Join the Discord

If you want to be a part of a supportive community of engineers (non-engineers welcome!) working to improve their lives and careers, join us on the Developer Tea Discord community by visiting https://developertea.com/discord today!

🧡 Leave a Review

If you're enjoying the show and want to support the content head over to iTunes and leave a review! It helps other developers discover the show and keep us focused on what matters to you. Leaving a review on iTunes is the most impactful way to help others find the show. The podcast is also available on Spotify and YouTube.

Transcript

The Fundamental Skill of Vocabulary

Fundamental skills that will carry you through the most difficult parts of your career. It'll carry you through the transitions in your career. It'll carry you through disruptions like what we're experiencing right now with AI. It'll carry your carry you through uh from title changes, from hopping tracks, let's say you're an engineer and you want to become a manager. The fundamental mindset that I want to reinforce to remind you of today is the mindset of building your vocabulary.

Building your vocabulary. And to be clear, uh I partially mean building your literal vocabulary. But it goes beyond that. And it's part of the uh fundamental mission of this show, of this podcast. To help developers, to help engineers, software engineers, data analytics engineers, product engineers, front end developers. Uh people who are building things, whoever you are, you probably count in this, okay? To help you find clarity, perspective, and purpose in your career.

and finding clarity Finding perspective and even finding purpose. Those efforts rely on the the mental tooling that we talk about so much on this show. How do you find clarity? How do you find perspective? How do you find your purpose? And the first building blocks are your vocabulary. So when we talk about mental models on this show, that is a form of vocabulary. The mental model concepts that you build, that lattice work.

That is part of your vocabulary because it will help you in attaining, for example, clarity. A mental model can help you in attaining perspective. A model can even help you in understanding purpose. Building your vocabulary is also about understanding your own self, the granularity of your own self. You know, we've heard stories about

how there are different words in different languages. You can Google this. I don't have a sp a good specific example for this, but uh I'll I'll make something up here. For example, there may be so many words for the underlying concept of love. And a given language may have a really specific articulation of a feeling, an idea. uh that another language doesn't have. So this nuanced explanation. the nuanced vocabulary, uh, the ability to combine these ideas together.

This uh is a good analogy for understanding the variety of, for example, personal values you hold. Understanding the way that you respond under stress. the kinds of things that you care about over time, how do you operate in a high intensity environment? These are all pieces of your personal kind of intellectual, emotional, spiritual, uh, whatever, uh, you know, A L word you want to use here, uh, these are all types of vocabularies that you can develop for yourself.

Beyond Words: Concrete Examples

Another another more concrete example of this that I've experienced in my personal life is understanding different forms Uh in in my personal life, I I mean in my personal career life, understanding different forms of diagrams is very simple uh, you know, vocabulary that I've been working on recently. Understanding, for example, what is a causal loop diagram? Now what's really interesting is that

We can build our vocabulary and then we can take advantage of this vocabulary in new and unique ways. Another good example of this, there are paradigms in programming. Paradigms and and uh design patterns, those kinds of uh kind of models, ways of thinking about things. So if you have never experienced, for example, the asynchronous paradigm or the event driven architectural paradigm,

uh then those pieces of vocabulary, which may be useful, again, these are kind of like mental models, right? They may be useful in multiple contexts, uh, but y you won't have access to those until you learn that vocabulary. Right, so uh this is something that even Paul Graham talked about. He talked about the idea that uh, you know, understanding something like small talk provided a unique advantage.

That was a kind of a leap ahead of other programming languages because it has a fundamentally different paradigm. Uh there are there are parts and pieces of how you would use small talk that uh that that don't have a good analogue with other languages. Vocabulary. has been useful uh to Paul Graham and many, many other engineers who have found tools that express what they are thinking in more uh nuanced or more powerful, higher leverage ways.

Leveraging LLMs for Conceptual Expansion

If you are able to develop this vocabulary, and I would say you have an opportunity to uh continue refining this vocabulary by learning about it and exploring the nuances of it with. uh with an LLM, for example, you are going to be able to wield a more uh complete Kind of picture. um uh in whatever endeavor you're you're moving into. So for example, if I wanted to explore a subject that I've never uh that I've never thought about before. Now I have some some tools at my disposal.

Uh I will, you know, search for various systems and try to develop an understanding of the causal loops in the system that's at play. This helps me get a picture for what kinds of things are happening. Where are the leverage points? What might I do to change things, to balance something out?

You know, what does the system look like? And I can do a lot of this work now uh just by having the vocabulary. I don't necessarily have to have you know, uh, every piece of skill underlying skill or or perfection of that vocabulary. But having that top level uh and understanding those concepts so I can piece them together, this is probably the most valuable skill. that I've learned that I've picked up in my career, the ability to add to your repertoire, um, to add to your overall vocabulary.

Some of these ways of thinking. Um I I won't limit it to mental models because I do think it goes beyond that, that the concept of a mental model captures some parts of this, but it's not entirely complete. Um, you know, for example, understanding what a what a C four diagram This is a piece of vocabulary. It might be, you know, uh you you could kind of squint and call that a mental model, but really it's just

some vocabulary and uh and here I I you know I want to be careful that you understand what I mean when I say vocabulary. I really mean conceptual vocabulary. I I don't mean just one word, but also what the connotation of that word, where does it come from? When is it useful? How does it piece together with other things that are adjacent? You know, when when would you care about seeing a C four diagram versus say a a pipeline, uh, you know, that kind of uh uh you know, charting.

There are plenty of opportunities to develop your vocabulary as you learn uh about these various things. Well, you know, one one way that I would suggest that you pick up um as soon as possible. is to start with the fundamental kind of primitives, the principled pieces. of your system. Think about the inputs, the outputs, the flows.

Is this a static system? Is it a dynamically changing system? You know, the thinking in these systematic terms can help you understand what are the primitive uh you know interacting pieces. And then you can think about, okay, you know, what what am I trying to get out of this? And am I trying to understand, you know, how these things work over time? Maybe there is some kind of time series graph that would be a piece of vocabulary.

Uh so you know one one uh incredibly useful tool in this regard, and I won't recommend using LLMs for everything in your life, but this is a place where an LLM does a fairly good job. And the reason for that is because you can describe these primitives and you can ask uh you know, essentially ask questions and because of the way LLMs are trained and because of how uh the the kind of lookup will work, you're going to find something that many people uh have likely used for that type of primitive.

So if you had XY data, you're likely to find a scatterplot graph as a tool that you might use to visualize that XY data. Um this is a remarkably good tool for expanding your vocabulary for that reason.

Higher Leverage: Understanding Why and When

Thank you so much for listening to today's episode of Developer T. I hope you will make it a point. uh you know in your learning journey in particular, make it a point to always be expanding your vocabulary. This means that you're looking for the leverage points at the categorical level. You're not just looking to you know, add a little skill here and there. You're not just looking to learn how to use a thing.

Right. Um that is a lower leverage um change to your skill level. Right. The much higher leverage is to know why you're using that thing in that context. Why would you use that thing instead of another thing? When would you use something different? Uh, you know, how can you piece together your various pieces of vocabulary to get the things that you care about, to get the insights that you care about, et cetera. Thanks so much for listening.

Uh, if you enjoyed this episode, please let me know. Uh you can join the Developer T Discord community. Head over to developer t.com slash discord. I'm in there and so are a bunch of other engineers who listen to this show regularly. Um, you can also email me. We don't talk about the email. but developer t at gmail.com. You can email me questions. Another great way to leave a comment uh about the show is to leave a review. Leave a review in iTunes, whatever possible. Others find that review.

Make a decision about listening to the show. Of course we're on uh Spotify, we're on on YouTube as a podcast. find that there as well. Thanks so much for listening and until next time.

This transcript was generated by Metacast using AI and may contain inaccuracies. Learn more about transcripts.
For the best experience, listen in Metacast app for iOS or Android