Friday Recap - 2025/04/11
Life long exploration and AI-rubber-ducking.
The Art of Exploration is a Lifelong Pursuit
Our world is too dynamic to ever stop exploring.
I episode 1,062 of The Art of Manliness, The Art of Exploration — Why We Seek New Challenges and Search Out the Unknown, Brett McKay interviews Alex Hutchinson, author of The Explorer’s Gene.
They touch on the explore-exploit problem: when do you stop exploring new things and double down on what you know works?
I won’t get into the details, check out Alex’s book and Algorithms To Live By for a deep dive on the topic, but in short, the rational solution would be to progressively explore less and exploit more. The older we get, the less we should explore.
But while the math does not lie, there’s something uncomfortable with the idea of stopping to explore, isn’t there? Does being rational mean giving up on novelty and settle for eating the same meal at the same restaurant, listening to the same album, and re-watching the same movie?
Brett and Alex both agree that there must be more to it than the raw math, and offer two reasons for why one ought to keep exploring.
The first is that as our life expectancy increases, we can explore for many more years than our ancestors. I don’t like this explanation because it simply pushes the problem later in the future. That we can explore in our sixties does not address what to do in our eighties. Besides, one could argue that since we live longer we have more time to exploit and accrue benefits that way.
The second reason Brett and Alex offer for continuing to explore is that exploring simply feels good. Once you factor into the explore-exploit model the value you get from trying new things for the sake of it, mere exploitation becomes less attractive. Exploring is inherently valuable because it breaks monotony and gives us new experiences.
Here’s a third reason to add into the mix. We should keep exploring because the future does not resemble the past.
Explore-exploit assumes a static world. When nothing changes, finding a local maximum to exploit can indeed generate lots of value over time.
But our world is in constant flux. We live in a time where more and more is being created by more and more people thanks to technology liberating us from rote labor.
The more creativity, the more the future becomes unpredictable. The value landscape is fluid, the peak you find today might be greatly overshadowed tomorrow.
So, never stop exploring. Even the day before you die, keep exploring.
I’ll leave you with a quote often attributed to Mark Twain but that apparently comes from H. Jackson Brown, Jr. mother’s:
Twenty years from now you will be more disappointed by the things you didn’t do than by the ones you did do. So throw off the bowlines. Sail away from the safe harbor. Catch the trade winds in your sails. Explore. Dream. Discover.
Originally published on giolodi.com on 2025/04/09.
The Rubber Duck Now Quacks Back
Rubber ducking in the age of AI.
Large language models (LLMs) are versatile tools. You can use them as artificial interns1 to generate draft for you, feed them documents to summarize, proof read, and more. An LLM can generate a training plan for you, propose a travel itinerary, or help you adjust the tone of an important message you are writing.
Another way to put LLMs to work is for rubber ducking. But with a twist—the rubber duck quacks back!
Rubber ducking is a common practice among software developers. The name comes from The Pragmatic Programmers, where Dave Thomas recalls how a colleague used to work with a rubber duck on top his terminal and describe the problems he was stuck on to it.
When describing a coding problem out loud, “you must explicitly state things that you may take for granted when going through the code yourself.” This is often enough to generate insight into the problem and make progress. And this works in any creative field, not just programming.
Notice that it’s the act of describing the problem that is valuable. The result is the same whether you talk to a real person or to a rubber duck.
Talking to an inanimate object has the advantage of not distracting your colleagues. But there are times where describing a problem is not enough and you could benefit from a probing question or the push back.
So why not talk to an LLM?
With AI, rubber ducking takes on a new level. This digital rubber duck quacks back, can judge your idea, help you sharpen them, and suggest alternatives. All without disturbing your teammates.
With ChatGPT, Claude, Gemini, Grok, we all have at our fingertips a squad of interactive rubber ducks that are smart, patient, and always available.
But no matter how refined they are, we need to remember that LLMs are far from error-proof. On top of that, many LLMs will do their best to please you, but when problem solving it’s criticism that you need most.
You wouldn’t ship the work your intern made without first looking over it, whether the intern is a human or a bot. Likewise, you cannot trust everything a toy duck tells you, whether is made of rubber or bits.
Remember Feynman’s words: “You are the easiest one to fool.” Don’t let an LLM tuned to please its user lull you into thinking you discovered the best solution.
Dave Thomas’ rubber duck never validate your ideas, it only gave you space to understand them. These digital rubber ducks might quack back, but of all the work we ought to delegate to AI, thinking remains our responsibility.
1 — The article used DALL-E to show how much guidance a generative AI needs, and how many iterations are required to get to a satisfying result. Since then, image generation has leapfrogged both in prompt understanding and output quality. The intern has gotten much better, but it’s still an intern. AI has no initiative or genuine creativity. You need to tell it what to do.
Thanks to Alex Grebenyuk for the conversation that resulted in this post. In particular for the term “the rubber duck talks back.”