Freakonomics – Serenity Through Sweat

Prompt

Thanks for joining me for another edition of the SerenityThroughSweat blog.

AI has been in the news quite a bit recently with the continuing advancement of ChatGPT and the drama surrounding its upper management.

I came across some of the grassroots origin of AI, in the form of computational linguistics, while continuing research on my communications project.

I am far from a subject matter expert on AI, language, or communication, but here is my two cents nonetheless. And, you should take it, we are due for a recession anyway.

Computational linguistics really began as a field before it ever had a chance. By that I mean the right tools for the job hadn’t even been invented yet.

ChatGPT and other Large Language Models, LLM’s, require enormous datasets and computing power. Before the internet, and the personal computer, this meant manual entry and analysis of all those words.

The LLMs function less by looking at the “rules of language”, and more by analyzing the likelihood of what the answer should be based on existing information.

From the analysis on computational linguistics, “Members of the IBM research team flaunted their ignorance of linguistics as if to taunt the other researchers. Fred Jelinek is famously quoted as saying, ‘Every time I fire a linguist from our project, the performance of our system gets better’

How fast can you squeeze out the toothpaste? Now, how fast can you put it back in? Our words work the same way

I think the easiest way to think about these LLM’s is as probability engines. This work was pioneered by Claude Shannon (whose work I have covered in quite a few other posts)

The LLM absorbs and analyzes a huge amount of data. An unimaginable amount of data. Think about reading the entire contents of the internet. Every tweet, every news article, every blog. Then statistically analyzing all those words to look for patterns.

From a previous post covering the work of Shannon, “As Shannon showed, this model also describes the behavior of messages and languages. Whenever we communicate, rules everywhere restrict our freedom to choose the next letter and the next pineapple*” “Because you’re completely aware of those rules, you’ve already recognized that ‘pineapple’ is a transmission error. Given the way the paragraph and the sentence were developing, practically the only word possible in that location was ‘word’ “

A beautiful day for a run on a Montreal layover

When Shannon completed his mathematical theory of communication, the internet wasn’t even a pipe dream, and he did a tremendous amount of work developing the earliest computers.

His theories and ideas, though, would pave the way for how these LLMs operate. They look for patterns by searching and analyzing all of the current written work on a topic. They then recombine words in a statistically viable way to answer questions

You can debate whether or not this constitutes, learning, or understanding, or consciousness, but that’s not really the point. It is here now, in this current form, and it can be an extremely useful tool. It can also spit out unintelligible garbage. So how do you engage with LLMs in a way that is useful and productive?

I think the answer has already been covered in the AI action warning movie Irobot. “My responses are limited, you must ask the right questions”

In this light, the rise of ChatGPT and other LLMs has led to the creation of a new host of jobs, one of which is the prompt engineer.

I first heard about the prompt engineer from episode 556 of the freakonomics podcast.

Prompt engineers discern what it is that their customer wants, and then find a way to effectively communicate that to the LLM.

Asking the right questions, adding the right context and constraints, make all the difference. If you think about it, the same concept applies to communicating with our kids. Or with other adults who may be operating outside their area of expertise.

If you want your five year old to do something, you need to set up some guideraills, and provide clear expectations. If you want a coworker to complete a new task, you need to provide the context and desired outcome, in order to get the finished product you want.

LLMs function much like the very intelligent five year old. You can be amazed what they are able to produce if given the right prompt.

Sometimes, it is hard to know what exactly we want. It is even harder to find the right combination of words to effectively transmit that want to someone else. Asking the right questions, setting the right context and guardrails, can help us in the endeavor. Finding the right prompt, might just lead to some serenity.

Trying to keep the mileage up in my pseudo off-season

Thanks for joining me, stay safe and stay sweaty my friends.

Quitting

Thanks for joining me for another edition of the SerenityThroughSweat blog. This week I want to talk about quitting. That may seem like an odd message for what is typically a more upbeat and positively oriented platform, but hear me out.

Author of The Voltage Effect, John List was on the freakonomics podcast discussing his book and his overall economic philosophy. The book is an economist’s ideas on how to make entrepreneurial ideas work at scale.

The conversation covered a number of cases studies including Uber, Lyft, and K-mart. Specifically discussed was the K-mart blue light special.

The blue light special (along with K-mart) went from being a sales mogul, to a forgotten cultural relic. Lost to the annals of history along with Kodak and Blockbuster.

The blue light special would alert shoppers to a great deal on individual products that were then first come first serve until they were gone. The resulting increase in sales not just for the blue light product but for all products was astonishing.

Taking advantage of excitement, scarcity, and a feeling of exclusivity, the blue light special was a smash hit. Until it was taken over by corporate. individual store managers could set the blue light special for their customers needs in a way that was inaccessible to corporate offices. Not to mention that the shoppers in Boise probably had different wants than those in Orlando.

Among other decisions and macro trends outside of their control, K-mart fell by the wayside. List discusses some of these trends but laments corporate inability to shift from a bad plan. When the desired outcome is not being served by a plan it is time to quit. This is what he calls optimal quitting.

Quitting has a decidedly negative connotation, and especially for the many endeavors that I pursue, grappling and triathlon among others. But within each of those activities are dozens of optimal quitting scenarios.

Abandoning a technique that has been cleverly countered. Switching to a different game plan or overall strategy for an opponent with different skill sets. Changing your race pace or gearing based on race day terrain or conditions. These are all examples of optimal quitting. Real time adjustments when the desired outcome is not being served.

Parenting presents plenty of opportunities for optimal quitting too. Wrestling with my boys is all fine and well until it escalates, or gets them too riled up before bed. There is undoubtedly and optimal time to quit. One that is often times slightly exceeded.

The tools used to tackle a tantruming toddler can vary in their approach. Using one too long may preclude using another. If you use the stick too early, it is hard to dangle the carrot. If they’ve already got the carrot the stick doesn’t hold the same power. There is a period of optimal quitting when changing your tactics with a toddler. One I have yet to figure out.

The point is, quitting is not the end all be all of negativity it is often painted to be. Practice quitting, especially optimally quitting, is worth your time and energy. As someone who has stumbled into doing it correctly on occasion, whether it be grappling, parenting, or grappling with my parenting dilemma, optimal quitting can yield its own form of serenity.

Tour de Zwift, running and some KOT programming

Thanks for joining me, stay safe and stay sweaty my friends.

Questions

Thanks for joining me for another edition of the SerenityThroughSweat blog. Election season is upon us, my work group is in the middle of a contract amendment vote, and all of us are analyzing how we adjust to COVID-19 measures in our day to day life. To be successful in any of these or many another endeavors requires asking questions, specifically, asking the right questions.

I just finished reading Freakonomics, the book by Stephen Dubner and Steven Levitt. For a book that claims to have no underlying theme, it is really a book about asking the right questions before accepting information that is provided.

The various topics themselves (while interesting) are really the backdrop for the true value in the book, which illuminates why we act the way we do. Most topics start with some assumption of the outcome, and then examine the incentives in place that help shape human behavior. The authors write, “Incentive is a tiny object with astonishing power to change a situation”.

As the book goes on, the questions asked generally challenge the conventional wisdom on a particular topic. After positing a question that challenges a typically held belief, the authors then go in search of data, that is run through unemotional regression analysis to isolate variables that are correlated. The results often clash head on with the conventional wisdom

There are several examples in the book that studied early learning test scores (K-5) and various parenting statistics both active and passive (age before kids were born, education level, spanking, screen time, one parent home between age 0-5). As a parent I was very interested to find out that the most highly correlated factors affecting test scores were either genetic or socio-economic, prior to your child’s birth. In other words, your life prior to becoming a parent has more impact on your child’s early test scores, than any of the at home pre-K educational work you can do. (Not that it hurts at all, it just isn’t statistically significant)

While this information is both fascinating and relieving (my boys aren’t doomed because I travel for work), it is the question that is far more valuable. The question being, what can I do as a parent to help my children be successful?

El Duderino helping out with the post workout shake, “Ma, where’s the protein?”

The answer is well beyond the scope of this blog, (although I believe being a role model for general well-being is a great start). Asking the right questions and searching for answers, not accepting what is thrust forth against the data, is another great place to start.

The same applies to the personal well-being, diet and exercise world. There are plenty of conventional wisdom trends that have recently been upended, from high fat low carb eating, to high intensity interval training, to intermittent fasting and fat adapted endurance athletes, the data show a myriad of possibilities that were shunned just a few years ago. Again, for the scope of this blog the individual programs are less important than the questions, what am I doing to be a better version of myself? Does the data support those decisions/programs?

For all of my colleagues voting on the contract amendment, I urge you to ask yourself, what is my incentive, and have I examined the data, rather than the popular narrative?

For all of us approaching election season I urge you to ask yourself, have I researched the issues and the positions rather than the popular sound bytes?

For your own personal growth are you doing the things you can to be better than you were yesterday? I hope you will join me on the path of asking ourselves the tough questions, and maybe even getting a little sweaty along the way.

Thanks for joining me, start safe and stay sweaty my friends.