Crypto failed because its desire was to remove humans. Its biggest failure — or was it a feature? — was that when the technology went awry and you needed somebody to step in, there was nobody.

Ultimately, we all want to appeal to another human to be seen and understood — not to a machine running a model.

Interacting with each other is the whole point.

I’ve never wanted to promote myself.

I’ve never wanted to argue with people on the internet.

I’ve never wanted to sue anyone.

I want to make my little thing and put it out in the world and hope that sometimes it means something to somebody else.

Without exploiting anyone.

And without being exploited.

If that’s possible.

Sometimes, when I use LLMs, it feels like I’m consulting the wisdom of literally everyone who came before me.

And the vast compendium of human experiences is undoubtedly complex, contradictory, painful, hilarious, and profound.

The copyright and ethics issues surrounding AI are interesting to me because they feel as those we are forcing software engineers and mathematicians to codify things that we still do not understand about human knowledge.

If humans don’t have a definitive answer to the trolly problem, how can we expect a large language model to solve it?

How do you define fair use? Or how do you value knowledge?

I really feel for the humans who just wanted to create things on the internet for nothing but the joy of creating and sharing.

I also think the value we collectively receive when given a tool that can produce pretty accurate answers to any of our questions is absurdly high.

Anyway, check out this really great comic, and continue to support interesting individuals on the internet.

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.