The scribbler, the scribe, the sculptor.

Vibe coding has become the term for the exercise of using AI to make software with little regard for the specifics, ostensibly hand-waving ideas into applications instead of taking time to design and build robust architectures in the 'old way'. It is used both derogatorily by the old and embracingly by the new.

The old guard resists, writing off the vibe coder as a fool, an amateur and vain artiste, without dexterity nor experience. The new guard writes off the old guard as pious dogmatists with sacred obsessions, needlessly gate-keeping new learners and impassioned builders alike.

It is my feeling that the role of one who uses AI to aid in the creation of software should not be diminished to vibes. There are many forms of aid and many forms of programming amidst various levels of abstraction. With some forms, you must know the hardware in-and-out; with others, you must only know a succinct syntax with which to operate a specific interface. Just as I do not need to concern myself with memory allocation or garbage collection in the programming languages I use, I soon too will not care or need to know how many arguments a function takes or which return type I should expect. These details will become lost from sight, layered beneath the form I deal with. Much like memory performance and stack-traces sit in a debugging interface, so too will the code itself, accessed and mutated only when problems arise.

Whether we like it or not, Natural Language itself is soon to be the lingua franca of programming. It will become a tool more important than perhaps any other in how we drive technology. Its utility will soon extend far beyond that of communicating with other humans. We must now wield it to talk to machines. However, like wielding a trébuchet to create a fine piece of jewellery, it is often an imprecise brute. But if we move the language closer to the thing itself, we can see with greater leverage how it forms our creations, and thus direct its aim better to our end.

We may start with a scribble–or vibe–but there is an art and skill to moving into, around and out of the specifics of our creations, to address every need with well-targeted prescriptions. In these early days, however, to accomplish this we need to know our material, the meat of software-engineering itself, inside-and-out. We may begin as scribblers with vague notions, then advance to scribes with some technical understanding. But ultimately, we must aspire to be sculptors who with each word change the aim of our tool to react to how our material last reacted to us. A collaboration between ourselves, the tool, and the material that we shape.

I wish into our new lexicons the scribbler, the scribe, and the sculptor:

• (~vibes) The scribbler is a noodler, a thinker, an imagineer, someone with a vision who wants to form something material from a need or idea.
• (~prompts) The scribe is a competent software crafter who can take scribbles and form them into natural language that directs knowable idiomatic software outcomes from an AI, and is able to verify and make manual changes when necessary.
• (~collaboration) The sculptor is the evolved practitioner who truly collaborates with AI, responding to its outputs and shaping the material together through deep understanding of both the material and the AI's idiosyncracies and eco-system.

I don't prescribe that an engineer is a sculptor, nor a writer a scribbler, but we humans do not yet have the words for these new evolving roles, so borrowing such terms from other artisanal forms is useful.

A word of warning, however, to anyone taking up new mantles in the era of AI: it is not looked kindly upon to take to a role that others deem evasive of hard work. Even if they are wrong.

By James.

Thanks for reading! :-)