Current generative AI systems like ChatGPT employ user interfaces driven by “prompts” entered by users in prose format. This intent-based outcome specification has excellent benefits, allowing skilled users to arrive at the desired outcome much faster than if they had to manually control the computer through a myriad of tedious commands, as was required by the traditional command-based UI paradigm, which ruled ever since we abandoned batch processing.

But one major usability downside is that users must be highly articulate to write the required prose text for the prompts. According to the latest literacy research, half of the population in rich countries like the United States and Germany are classified as low-literacy users.

This might explain why I enjoy using these tools so much.

Writing an effective prompt and convincing a human to do a task both require a similar skillset.

I keep thinking about how this article impacts the barefoot developer concept. When it comes to programming, sure, the command line barrier is real.

But if GUIs were the invention that made computers accessible to folks who couldn’t grasp the command line, how do we expect normal people to understand what to say to an unassuming text box?

I have this dream for barefoot developers that is like the barefoot doctor.

These people are deeply embedded in their communities, so they understand the needs and problems of the people around them.

So they are perfectly placed to solve local problems.

If given access to the right training and tools, they could provide the equivalent of basic healthcare, but instead, it’s basic software care.

And they could become an unofficial, distributed, emergent public service.

They could build software solutions that no industrial software company would build—because there’s not enough market value in doing it, and they don’t understand the problem space well enough.

And these people are the ones for whom our new language model capabilities get very interesting.

Do yourself a favor and read this entire talk. Maggie articulated the general feeling I have felt around the promise of LLMs within the confines of a concise, inspiring talk.

A friend approached me a few months back and asked me to help him build an app to facilitate a game he likes to play with his friends in real life.

I told him that a good first step would be to experiment first with facilitating the game using good ol’ fashioned paper, and use the lessons learned from that experience to eventually build an app.

A few weeks later, he came to me with a fully baked version of the app in a prototyping tool called AppSheet.

I was stunned at how much he was able to get done without any professional development support.

He’s a prime example of a barefoot developer. I don’t think he has any interest in crossing the “command line wall,” but as these tools get more capable, it’ll enable him and scores of others to build software that’ll solve their problems for them.

Helping more “normal people” to become barefoot developers is a cause I’d love to be part of.