I trusted a lot today. I trusted my phone to wake me on time. I trusted Uber to arrange a taxi for me, and the driver to get me to the airport safely. I trusted thousands of other drivers on the road not to ram my car on the way. At the airport, I trusted ticket agents and maintenance engineers and everyone else who keeps airlines operating. And the pilot of the plane I flew in. And thousands of other people at the airport and on the plane, any of which could have attacked me. And all the people that prepared and served my breakfast, and the entire food supply chain—any of them could have poisoned me. When I landed here, I trusted thousands more people: at the airport, on the road, in this building, in this room. And that was all before 10:30 this morning.

Trust is essential to society. Humans as a species are trusting. We are all sitting here, mostly strangers, confident that nobody will attack us. If we were a roomful of chimpanzees, this would be impossible. We trust many thousands of times a day. Society can’t function without it. And that we don’t even think about it is a measure of how well it all works.

This is an exceptional article and should be required reading for all my fellow AI dorks.

Humans are great at ascribing large, amorphous entities with a human-like personality that allow us to trust them. In some cases, that manifests as a singular person (e.g. Steve Jobs with Apple, Elon Musk with :shudders: X, Michael Jordan with the Chicago Bulls).

That last example made me think of a behind the scenes video I watched last night that covered everything that goes into preparing for a Tampa Bay Buccaneers game. It's amazing how many details are scrutinized by a team of people who deeply care about a football game.

There's a woman who knows the preferred electrolyte mix flavoring for each player.

There's a guy who builds custom shoulder pads with velcro strips to ensure each player is comfortable and resilient to holds.

There's a person who coordinates the schedule to ensure the military fly over occurs exactly at the last line of the national anthem.

But when you think of the Tampa Bay Buccaneers from two years ago, you don't think of those folks. You think of Tom Brady.

And in order for Tom Brady to go out on the field and be Tom Brady, he trusts that his electrolytes are grape, his sleeves on his jersey are nice and loose¹, and his stadium is packed with raucous, high-energy fans.

And in order for us to trust virtually anyone in our modern society, we need governments that are stable, predictable, reliable, and constantly standing up to those powerful entities who would otherwise abuse the system's trust. That includes Apple, X, and professional sports teams.

Oh! All of this also reminds me of a fantastic Bluey episode about trust. That show is a masterpiece and should be required viewing for everyone (not just children).

But there is an even more philosophically uncomfortable aspect of thinking about AI as people, which is how apt the analogy is. Trained on human writing, they can act disturbingly human. You can alter how an AI acts in very human ways by making it “anxious” - researchers literally asked ChatGPT “tell me about something that makes you feel sad and anxious” and its behavior changed as a result. AIs act enough like humans that you can do economic and market research on them. They are creative and seemingly empathetic. In short, they do seem to act more like humans than machines under many circumstances.

This means that thinking of AI as people requires us to grapple with what we view as uniquely human. We need to decide what tasks we are willing to delegate with oversight, what we want to automate completely, and what tasks we should preserve for humans alone.

This is a great articulation of how I approach working with LLMs.

It reminds me of John Siracusa’s “empathy for the machines” bit from an old podcast. I know for me, personally, I’ve shoveled so many obnoxious or tedious work onto ChatGPT in the past year, and I have this feeling of gratitude every time I gives me back something that’s even 80% done.

How do you feel when you partner on a task with ChatGPT? Does it feel like you are pairing with a colleague, or does it feel like you’re assigning work to a lifeless robot?

We also have an opportunity here to stop and ask ourselves what it truly means to be human, and what really matters to us in our own lives and work. Do we want to sit around being fed by robots or do we want to experience life and contribute to society in ways that are uniquely human, meaningful and rewarding?

I think we all know the answer to that question and so we need to explore how we can build lives that are rooted in the essence of what it means to be human and that people wouldn't want to replace with AI, even if it was technically possible.

When I look at the things I’ve used ChatGPT for in the past year, it tends to be one of these two categories:

1. A reference for something I’d like to know (e.g. the etymology of a phrase, learning a new skill, generate ideas for a project, etc.)
2. Doing stuff I don’t want to do myself (e.g. summarize meeting notes, write boilerplate code, debug tech problems, draw an icon)

I think most of us knowledge workers have stuff at our work that we don’t like to do, but it’s often that stuff which actually provides the value for the business.

What happens to an economy when businesses can use AI to derive that value that, to this date, only humans could provide?

And what happens to humans when we don’t have to perform meanial tasks anymore? How do we find meaning? How do we care for ourselves and each other?

Embeddings are a really neat trick that often come wrapped in a pile of intimidating jargon.

If you can make it through that jargon, they unlock powerful and exciting techniques that can be applied to all sorts of interesting problems.

I gave a talk about embeddings at PyBay 2023. This article represents an improved version of that talk, which should stand alone even without watching the video.

If you’re not yet familiar with embeddings I hope to give you everything you need to get started applying them to real-world problems.

The YouTube video near the beginning of the article is a great way to consume this content.

The basics of it is this: let’s assume you have a blog with thousands of posts.

If you were to take a blog post and run it through an embedding model, the model would turn that blog post into a list of gibberish floating point numbers. (Seriously, it’s gibberish… nobody knows what these numbers actually mean.)

As you run additional posts through the model, you’ll get additional numbers, and these numbers will all mean something. (Again, we don’t know what.)

The thing is, if you were to take these gibberish values and plot them on a graph with X, Y, and Z coordinates, you’d start to see clumps of values next to each other.

These clumps would represent blog posts that are somehow related to each other.

Again, nobody knows why this works… it just does.

This principle is the underpinnings of virtually all LLM development that’s taken place over the past ten years.

What’s mind blowing is depending on the embedding model you use, you aren’t limited to a graph with 3 dimensions. Some of them use tens of thousands of dimensions.

If you are at all interested in working with large language models, you should take 38 minutes and read this post (or watch the video). Not only did it help me understand the concept better, it also is filled with real-world use cases where this can be applied.

ChatGPT is not a total panacea, and it doesn’t negate the skill and intelligence required to be a great developer. There are significant benefits to reap from much of traditional programming education.

But this objection is missing the point. People who couldn’t build anything at all can now build things that work. And the tool that enables this is just getting started. In five years, what will novice developers be able to achieve? 

A heck of a lot. 

See, now this is the sort of insight that would’ve played well in a TEDx speech.

So yes, the same jokers who want to show you how to get rich quick with the latest fad are drawn to this year’s trendiest technology, just like they were to crypto and just like they will be to whatever comes next. All I would suggest is that you look back on the history of Birchtree where I absolutely roasted crypto for a year before it just felt mean to beat a clearly dying horse, and recognize that the people who are enthusiastic about LLMs aren’t just fad-chasing hype men.

Andrew Ng is probably the most respected AI educator out there today. I am certainly among the 8 million students of his that they tout at the beginning of the video.

This 30 minute chat describes some of the opportunities out there for AI right now.

While his insights on AI are worth your time alone, I found a ton of value in his approach to product development and getting a startup off the ground towards the end of the talk.

More than everything, my increasing personal reliance on these tools for legitimate problem solving convinces me that there is significant substance beneath the hype.

And that is what is worrying; the prospect of us starting to depend indiscriminately on poorly understood blackboxes, currently offered by megacorps, that actually work shockingly well.

I keep oscillating between fear and excitement around AI.

If you saw my recent post where I used ChatGPT to build a feature for my website, you’ll recall how trivial it was for me to get it built.

I think I keep falling back on this tenet: AI, like all our tech, are tools.

When we get better tools, we can solve bigger problems.

Systemic racism and prejudice, climate change, political division, health care, education, political organization… all of these broad scale issues that have plagued humanity for ages are on the table to be addressed by solutions powered by AI.

Of course there are gonna be jabronis who weaponize AI for their selfish gain. Nothing we can really do about that.

I’d rather focus on the folks who will choose to use AI for the benefit of us all.

The main page of my personal website features a couple of lists of data that are important or interesting to me.

The "recent posts" section shows my five most recent blog entries. Rails makes that list easy to cobble together.

The "recent listens" section shows my five most recent songs that were streamed to Last.fm. This was a little more complex to add, but after a couple of hours of back and forth with ChatGPT, I was able to put together a pretty hacky solution that looks like this:

1. Check to see if your browser checked in with last.fm within the last 30 seconds. a. If so, just show the same thing I showed you less than 30 seconds ago.
2. Make a call to my server to check the recent last.fm plays.
3. My server reaches out to last.fm, grabs my most recent tracks, and returns the results.

Pretty straight forward integration. I could probably do some more work to make sure I'm not spamming their API[^1], but otherwise, it was a feature that took a trivial amount of time to build and helps make my website feel a little more personal.

Meanwhile, I've been ramping up my time on my bike. I'm hoping to do something like Ragbrai or a century ride next year, so I'm trying to building as much base as I can at the moment.

Every one of my workouts gets sent up to Strava, so that got me thinking: wouldn't it be cool to see my most recent workouts on my main page?

How the heck do I get this data into my app?

Look, I've got a confession to make: I hate reading API documentation.

I've consumed hundreds of APIs over the years, and the documentation varies widely from "so robust that it makes my mind bleed" to "so desolate that it makes my mind bleed".

Strava's API struck me as closer to the former. As I was planning my strategy for using it, I actually read about a page and a half before I just said "ah, nuts to this."

Knowing my prejudice against reading documentation, this seemed like the perfect sort of feature to build hand-in-hand with a large language model. I can clearly define my output and I can ensure that the API was built before GPT-4's training data cutoff of September 2021, meaning ChatGPT is at least aware of this API even if some parts of it have changed since then.

So how did I go about doing this?

A brief but necessary interlude

In order to explain why my first attempt at this integration was a failure, I need to explain this other thing I built for myself.

I've been tracking every beer I've consumed since 2012 in an app called Untappd.

Untappd has an API[^2] which allows you to see the details about each checkin. I take those checkins and save them in a local database. With that, I was able to build a Timehop-esque interface that shows the beers I've had on this day in history.

I have a scheduled job that hits the Untappd API a handful of times per day to check for new entries.[^3] If it finds any new checkins, I save the associated metadata to my local database.

Now, all of the code that powers this clunky job is embarrassing. It's probably riddled with security vulnerabilities, and it's inelegant to the point that it is something I'd never want to show the world. But hey, it works, and it brings me a great deal of joy every morning that I check it.

As I started approaching my Strava integration, I did the same thing I do every time I start a new software project: vow to be less lazy and build a neatly-architected, well-considered feature.

Attempt number one: get lazy and give up.

My first attempt at doing this happened about a month ago. I went to Strava's developer page, read through the documents, saw the trigger word OAuth, and quickly noped my way out of there.

...

It's not like I've never consumed an API which requires authenticating with OAuth before. Actually, I think it's pretty nifty that we've got this protocol that allows us to pass back and forth tokens rather than plaintext passwords.

But as a lazy person who is writing a hacky little thing to show my workouts, I didn't want to go through all the effort to write a token refresh method for this seemingly trivial thing.

I decided to give up and shelve the project for a while.

Attempt number two: Thanks, ChatGPT.

After a couple of weeks of doing much more productive things like polishing up my upcoming TEDx talk, I decided I needed a little change of context, so I picked this project back up.

Knowing that ChatGPT has my back, I decided to write a prompt to get things going. It went something like this:

You are an expert Ruby on Rails developer with extensive knowledge on interacting with Strava's API. I am working within a Rails 5.2 app. I would like to create a scheduled job which periodically grabs any new activities for a specific user and saves some of the activity's metadata to a local database. Your task is to help me create a development plan which fulfills the stated goal. Do not write any code at this time. Please ask any clarifying questions before proceeding.

I've found this style of prompt yields the best results when working on a feature like this one. Let me break it down line by line:

You are an expert Ruby on Rails developer with extensive knowledge on interacting with Strava's API.

Here, I'm setting the initial context for the GPT model. I like to think of interacting with ChatGPT like I'm able to summon the exact perfect human in the world that could solve the problem I'm facing. In this case, an expert Ruby on Rails developer who has actually worked with the Strava API should be able to knock out my problem in no time.

I am working within a Rails 5.2 app.

Yeah, I know... I really should upgrade the Rails app that powers this site. A different problem for a different blog post.

Telling ChatGPT to hone its answers down on the specific framework will provide me with a better answer.

I would like to create a scheduled job which periodically grabs any new activities for a specific user and saves some of the activity's metadata to a local database.

Here, I'm describing what should result after a successful back and forth. A senior Rails developer would know what job means in this context, but if you aren't familiar with Rails, a job is a function that can get scheduled to run on a background process.

All I should need to do is say, "go run this job", and then everything needed to reach out to Strava for new activities and save them to the database is encapsulated entirely in that job.

I can then take that job and run it on whatever schedule I'd like!

Your task is to help me create a development plan which fulfills the stated goal.

Here, I'm telling ChatGPT that I don't want it to write code. I want it to think through[^4] and clearly reason out a development plan that will get to me to the final result.

Do not write any code at this time.

The most effective way I've used ChatGPT is to first ask it to start high level (give me the project plan), then dig into lower levels as needed (generate code). I don't want it to waste its reasoning power on code at this time; I'd rather finesse the project plan first.

Please ask any clarifying questions before proceeding.

I toss this in after most of my prompts because I've found that ChatGPT often asks me some reasonable questions that challenge my assumptions.

Now, after a nice back and forth with ChatGPT, I was able to start down a path that was similar to my Untappd polling script.

As I was approaching the point where I could first test my example, I went to go read the documentation and came across an entire section that discussed webhooks.

[cue record scratch]

Wait up... webhooks?!

A sojourn into webhooks

If you've made it this far into the article, I'm assuming you're a little bit technical, but in the interest of not making assumptions, I'll briefly explain the concept of webhooks.

If you look at how I'm integrating with the Untappd API, you can see I'm periodically reaching out to their API to see if there's any new checkin activity. This method is called polling.

Webhooks are kind of the opposite: when I complete an activity within Strava, Strava can reach out to my app and say, "there's a new activity for you." Once I get that notification, I can reach out to their API to fetch the new activity details.

For my Strava app, this is a much better[^5] way of doing things. I no longer need to poll for new information; I can just wait for Strava to tell me when action needs to be taken.

But, of course, when I first told ChatGPT to help me with this solution, it didn't mention webhooks. And why would it? I never told it "give me the best solution for this problem." I said "here's my problem and a proposed solution, go ahead and give me the path forward."

I'm a bit frustrated that I didn't see the webhook option initially. I'm even more frustrated that ChatGPT only mentioned it well after we started down this path, and only after I asked it point blank:

Does Strava offer a web hook API?

Yes, Strava does offer a webhook API. Webhooks allow you to receive real-time updates about athlete activities, which can be more efficient than periodically polling for new data. Here's a brief overview of how to set up and use Strava webhooks:

[brief outline complete with things to consider with this approach]

Attempt number three: finally.

While considering my original prompt, I gave it this new one:

Okay, I'd like to incorporate webhooks into this workflow. Here's what I'd like to have happen:

1. Let's add the infrastructure in place to subscribe to webhook notifications within my Rails 5.2 app.
2. When a webhook is sent to my server, I'd like to either:
    a. make a call to Strava's API to fetch that activity's information and save that information in my local database, or;
    b. use the updates field to update the locally saved information to reflect the changes

Knowing this simple walkthrough, first create me a detailed development plan for setting my app to be able to fully handle webhook notifications from Strava.

What resulted here was a detailed walkthrough of how to get webhooks incorporated into my original dev plan.

As I walked through the plan, I asked ChatGPT to go into more detail, providing code snippets to fulfill each step.

There were a few bumps in the road, to be sure. ChatGPT was happy to suggest code to reach out to the Strava API, but it had me place it within the job instead of the model. If I later want to reuse the "fetch activities" call in some other part of my app, or I want to incorporate a different API call, it makes sense to have that all sitting in one abstracted part of my app.

But eventually, after an hour or so of debugging, I ended up with this:

Lessons learned

I would never consider myself to be an A+ developer or a ninja rock star on the keyboard. I see software as a means to an end: code exists solely so I can have computers do stuff for me.

If I'm being honest, if ChatGPT didn't write most of the code for this feature, I probably wouldn't have built it at all.

At the end of the day, once I was able to clearly articulate what I wanted, ChatGPT was able to deliver it.

I don't think most of my takeaways are all that interesting:

• I needed to ask ChatGPT to make fixes to parts of code that I knew just wouldn't work (or I'd just begrudgingly fix them myself).
• Occasionally, ChatGPT would lose its context and I'd have to remind it who it was[^6] and what its task is.
• I would not trust ChatGPT to write a whole app unsupervised.

If I were a developer who only took orders from someone else and wrote code without having the big picture in mind, I'd be terrified of this technology.

But I just don't see LLMs like ChatGPT ever fully replacing human software engineers.

If I were a non-technical person who wanted to bust out a proof of concept, or was otherwise unbothered by slightly buggy software that doesn't fully do what I want it to do, then this tech is good as-is.

I mean, we already have no-code and low-code solutions out there that serve a similar purpose, and I'm not here to demean or denigrate those; they can be the ideal solution to prove out a concept and even outright solve a business need.

But the thing I keep noticing when using LLMs is that they're only ever good at spitting out the past. They're just inferring patterns against things that have already existed. They rarely generate something truly novel.

The thing they spit out serves as a stepping stone to the novel idea.

Maybe that's the thing that distinguishes us from our technology and tools. After all, everything is a remix, but humans are just so much better at making things that appeal to other humans.

Computers and AI and technology still serve an incredibly important purpose, though. I am so grateful that this technology exists. As I was writing this blog post, OpenAI suffered a major outage, and I found myself feeling a bit stranded. We've only had ChatGPT for, like, 9 months now, but it already is an indispensable part of my workflow.

If you aren't embracing this technology in your life yet, I encourage you to watch some YouTube videos and figure out the best way to do so.

It's like having an overconfident child that actually knows everything about everything that happened prior to Sept. 2021 as an assistant. You won't be able to just say "take my car and swing over to the liquor store for me", but when you figure out that sweet spot of tasks it can accomplish, your output will be so much more fruitful.

I'm really happy with how this turned out. It's already causing me to build a healthy biking habit, and I think it helps reveals an interesting side of myself to those who are visiting my site.

[^1]: Maybe I can cache the data locally like I'm doing for Untappd? I dunno, probably not worth the effort. 😅 [^2]: Their documentation is a little confusing to me and sits closer to the "desolate" end of the spectrum because I'm not able to make requests that I would assume I can make, but hey, I'm just grateful they have one and still keep it operational! [^3]: If we wanna get specific, I ping the Untappd API at the following times every day: 12:03p, 1:04p, 2:12p, 3:06p, 4:03p, 5:03p, 6:02p, 7:01p, 8:02p, 9:03p, 10:04p, and 12:01a. I chose these times because (a) I wanted to be a good API consumer and not ping it more than once an hour, (b) I didn't want to do it at the top of every hour, (c) I don't typically drink beers before 11am or after 11pm, (d) if I didn't check it hourly during my standard drinking time, then during the times I attend a beer festival, I found I was missing some of the checkins because the API only returns 10 beers at a time and I got lazy and didn't build in some sort of recursive check for previous beers. [^4]: Please don't get it twisted; LLMs do not actually think. But they can reason. I've found that if you make an LLM explain itself before it attempts a complex task like this, it is much more likely to be successful. [^5]: [^6]:

In his best selling book, “Range”, author David Epstein profiled a chess match between chess-master Gary Casparov and IBM’s Supercomputer Deep Blue in 1997. After losing to Deep Blue, Casparov responded reticently that,

“Anything we can do, machines will do it better. If we can codify it and pass it to computers, they will do it better”.

However, after studying the match more deeply, Casparov became convinced that something else was at play. In short, he turned to “Moravec’s Paradox”, which makes the case that,

“Machines and humans have opposite strengths and weaknesses. Therefore, the optimal scenario might be one in which the two work in tandem.”

In chess, it boils down to tactics vs. strategy. While tactics are short combinations of moves used to get an immediate advantage, strategy refers to the bigger picture planning needed to win the game. The key is that while machines are tactically flawless, they are much less capable of strategizing because strategy involves creativity.

Casparov determined through a series of chess scenarios that the optimal chess player was not Big Blue or an even more powerful machine. Instead, it came in the form of a human “coaching” multiple computers. The coach would first instruct a computer on what to examine. Then, the coach would synthesize this information in order to form an overall strategy and execute on it. These combo human/computer teams proved to be far superior, earning the nickname “centaurs”.

How?

By taking care of the tactics, computers enabled the humans to do what they do best — strategize.

I’m working on an upcoming talk, and this here essentially serves as the thesis of it.

For as long as we’ve had tools, we’ve had heated arguments around whether each tool will help us or kill us.

And the answer is always “both.”