Friday Updates: Prepping TimelineGPT for Launch, Viva la EmergentMind


This week consisted of Milan (Preceden’s designer) and I getting TimelineGPT (the AI content generator we’re working on) from 80% ready to ship to 98%. Lots of small, boring tasks like:

  • Figuring out the UX after users click the “Add to Timeline” button in the suggestions dialog. Do we close the dialog? Keep it open? If we keep it open, do we uncheck the suggestions they just added? Hide them completely?
  • Sometimes GPT returns 1 suggestion for a topic, other times 30. When it returns just 1, should Preceden automatically try again to generate more? But then when you combine the results, there can be duplicate suggestions, but not exactly identical, so how do you figure out how to make the final list unique?
  • Adding lots of unit tests to ensure everything works as intended and edge cases are handled.
  • Integrating into OpenAI’s moderation endpoint so users can’t try generating timelines for inappropriate topics.
  • Setting up attribution so I can tell which new customers upgraded after using the suggestions tool (which will be important since using the GPT API will cost money, and I’ll need to carefully monitor the ROI of this tool).
  • Debugging a weird bug that stemmed from using Ruby’s AASM gem with Delayed Job.

Hopefully can launch the v1 early next week, rolling it out to 25% of users and then monitoring costs and usage before ramping it up to 100% within a week or two.

Plus normal support and maintenance like fixing this lovely bug that has probably lost me a bit of money over the years:

LearnGPT EmergentMind

I renamed LearnGPT to EmergentMind for reasons outlined in this post. Feels like the right move long term.

Other things:

  • Last week Andrej Karpathy, one of the leading AI educators in the world, demoed LearnGPT in the first 2 minutes of his recent intro to GPT lecture on YouTube. That explains the traffic spike ūüďą.
  • Milan and I are working on a big redesign to the site which should ship late next week or early the following week. You’ll get to see the difference between what I can do as a developer who is adequate at design and what a talented designer is capable of ūüĆą.
  • I started an EmergentMind Discord which is up to 13 people. I definitely feel like an old man though figuring out how to use Discord. At the moment, I’m just sharing product updates in there. TBD what it winds up being long term.
  • Various updates to EmergentMind: adding an account page so users can manage their account, including deleting it if they choose, as well as changing their password and email (for users that signed up via email and password and not Google OAuth). Also added an “About” field there which is displayed on new profile pages for EmergentMind users. Here’s mine. Not a bad v1 profile page, but looking forward to Milan redesigning it in the future.
  • Spent some time exploring the prompt engineering space, which is the tentative direction I’m taking the site. There are already a lot of tools like EveryPrompt and some educational sites like that EmergentMind may or may not wind up competing with. We will see.

Thanks for following along! ūüôá‚Äć‚ôāÔłŹ

LearnGPT is now EmergentMind

Naming things is hard.

Shortly after ChatGPT launched at the end of November, I decided to build a site to share ChatGPT examples and eventually be the home to educational content to help people learn more about GPT.

To my surprise, there were a lot of relevant available .com domain names related to GPT, so I registered a bunch and asked for suggestions on Twitter for which to use for the site:

And so I chose LearnGPT and for the last month and a half that’s been the name of the site.

On its surface, it’s a great name for a site focused on teaching people about GPT.

But, it has some issues:

  • People kept referring to the site as “Learn” in conversation because saying “Learn GPT” is clunky. “How’s ‘learn’ doing?” (looking at you Dave…)
  • In two years will we still be talking about GPT or one of the many other Large Language Models (LLM) coming out? Incorporating content on the site about them would be awkward if the name of the site referenced GPT.
  • And most importantly, the name “Learn GPT” meant that the site would forever be constrained to being an educational site about GPT. That likely meant monetizing it down the road via an info product which wasn’t interesting to me at all, so much so that it almost led me to shut the site down.

The hunt for a new name

I wrote a little Ruby script to search for available .ai domain names, hoping to find one to rename LearnGPT to:

… but unregistered quality .ai domains are few and far between, so that approach didn’t lead to any good candidates for a new site name.

Then it occurred to me… I already own a great domain I can use for the site.


Around 2014 I got very interested in the concept of emergence and created a site called Emergent Mind to build little projects to explore the space more. In the end I wound up creating 10 interactive visualizations: Boids, Game of Life, Cellular Automata, Tree Growing, Biomorophs, The Evolution of Color, Animorphs, Forming a Planet, The Perceptron, and Neural Network.

You can still play around with them if you’d like courtesy of

EmergentMind archive

It dawned on me recently that the name “Emergent Mind” was a great description for the end result of these Large Language Models like GPT: a mind of sorts that emerges from the machine learning process.

I didn’t own the Twitter handle @EmergentMind but thankfully its owner was kind of enough to give it to me for free which solidified my decision to use it as the new name for LearnGPT.

What’s next for EmergentMind?

In the course of integrating GPT into Preceden recently, I realized just how difficult prompt engineering can be. You might have some task in mind for GPT or another LLM, but what’s the best way to ask the question to get a great answer? It’s as much of an art as a science, and I think there’s an opportunity to build a community around this nascent skill.

So, instead of focusing on GPT, I’ve decided to focus on building a site for people interested in prompt engineering. Imagine educational content, tools, and a Stack Overflow-like community all built from the ground up, infused with AI, to help people learn to communicate with these new AI technologies more effectively.

And the name is flexible enough that if that prompt engineering direction doesn’t make sense long term (will prompt engineering still be a thing in a few years?), it’s easy enough to pivot without another name change.

Here we go ūüöÄ.

How would an evolving website work?

As a web developer who is also interested in A/B testing and evolution,¬†it occurred to me that it would be fascinating to try to build¬†a website¬†that optimizes itself. I’ve been kicking around this idea for a while and wanted to share a few thoughts on it here to get feedback from anyone else that finds the idea promising.

Here’s the idea:

In traditional A/B testing, you specify multiple variations of some aspect of your site, measure which variation¬†performs the best, then make the winner the default, and repeat. The types of things you test can range from simple headline and button color tests to complex tests that affect the user’s entire experience with your site.

In all of these cases though you have to figure out what¬†variations you want to test. If you’re testing the headline, you need to specify¬†which¬†headlines you want to test. If you’re testing button color, you need to specify which colors to test, etc.

In the natural world,¬†we see¬†stunningly complex and optimized life forms that evolved little by little¬†over billions of years. Evolution is similar to A/B testing in a sense, except that in evolution¬†the variations happen by accident through genetic copying errors. Most of those mutations¬†decrease the organism’s odds of reproducing, but occasionally they confer a benefit that causes that organism to have a better chance at surviving and reproducing. When that happens, the mutation gets passed on and may eventually spread to the rest of species over time. That “simple” process is what has led to all of the variety of life on earth.

Optimizing a web page through evolution poses many issues though.

How do you algorithmically mutate something on the page? Could you write a function that generates variations of a headline? Maybe. Would those variations be any good? Would you trust it enough to deploy into production?

I bet by analyzing tens of thousands of webpages, you could algorithmically identify common headline wording structures. Then maybe you could write code that intelligently customizes those headlines to your service.

You might be able to do the same with design. If you tried to categorize hundreds of homepage layouts, I expect you’d probably wind up with 20-30 common layouts that cover 90%+ of websites. Could you then write an algorithm that automatically tweaks your site’s layout¬†to test these different layouts on¬†your visitors? Could you do the same with color schemes? Maybe.

There’s also the problem of statistical significance. Running a simple two variation A/B test can take a long time if you don’t get a lot of traffic. Trying to get significant results for¬†lots of algorithmically generated headlines might take forever. But maybe¬†there are ways around that like the multi-armed bandit algorithm.

To sum it up, I think you’d need the following: a way to intelligently generate mutations on headlines, buttons, layout, etc + a ton¬†of traffic or some novel¬†method for picking the best variations + an organization that is willing to try¬†such an experiment. It would not be easy, but I think it’s possible.

Imagine if it did work. Maybe your homepage converts users into sign ups at 10% now. You flip a switch, and in 6 months it increases your conversion rate 30% without any intervention on your part.

It would be revolutionary… if it worked.

The State of Emergent Mind

In 2014 I worked on a side project called Emergent Mind to learn more about AI, artificial life and related topics. The result was 10 interactive JavaScript visualizations ranging from Boids to neural networks.

I really enjoyed working on it and received¬†a lot of great feedback, but I had to put it on hold after the arrival of my son last fall. I’d say the projects took about 10 hours each on average so they weren’t that time consuming, but with a newborn, a fulltime job and other obligations and interests I had to put it on the backburner for a while.

I’ve been weighing in my mind¬†whether or not to resume work on it.

Here’s my thought process:

The Pros

  • AI and especially artificial life are fascinating to me. The fact that we are all here now is a testament to the incredible power of¬†emergence and evolution. If I won the lottery and never had to work again, I’d probably spend a good chunk of my time working on¬†projects¬†to¬†explore these areas.
  • AI¬†is¬†playing a larger and ever-increasing importance¬†in our lives. I think we’re going to see an explosion of AI-enabled products and services over the coming decades… hopefully in a good way. Devoting time to learning it now will position me well to play a part in that future.
  • My impression is that AI researchers¬†don’t tend to work on products and product people don’t tend to work on AI so there are probably a lot of opportunies at the intersection of the two.

The Cons

  • It’s hard. These 10 projects barely scratched the surface. My backpropagation post¬†is at about the limit of my current math¬†skills. I might (and that’s a big might) be able to teach myself, but flipping through PDFs of machine learning texts like The Elements of Statistical Learning¬†is pretty daunting. I could go back to school, maybe get a masters in machine learning, but that brings me to the next point…
  • There are huge opportunity costs. Every hour I spend learning and working on AI projects is one less hour I get to spend learning about growth, JavaScript, spending time with my wife and son, relaxing, etc. Given a choice between going from an intermediate JavaScript developer to an expert with a few months of work and going from a beginner at AI to an expert in 5-10 years of work it’s hard to justify the latter.
  • No one can say for sure how AI will play out, but the possibilities have a lot of smart people very concerned. Read this WaitButWhy post¬†for a great introduction and¬†Superintelligence by Nick Bostrom if you want to learn more.
  • I love building products, but just don’t have many practical applications in mind for this type of work. The state of the art machine learning work seems largely applied to things like computer vision (boring to me), self-driving cars (interesting, but hard to work on from my home office), increasing the accuracy of various prediction techniques¬†(somewhat interesting to me, but still no product in mind) and virtual assistants¬†(interesting, but¬†seems hard to compete with Facebook, Microsoft, Google, Apple, etc). It might just be a lack of imagination, but I can’t think of many¬†products at the intersection of web app development and AI that excite me. If I were to build something it would probably wind up being a product like¬†The Grid, though calling that AI seems more like a marketing move¬†than actual AI (what is actual AI though?).

So, for now anyway, I think Emergent Mind will continue to stay on the backburner. Maybe one day I’ll pick it up again. We’ll see.

I’d love to hear your thoughts.