I think some of the CEOs have it right on this one. What is going to get harder is selling “applications” that are really just user friendly ways of getting data in and out of databases. Honestly, most enterprise software is just this.

AI agents will do the same job.

What will still matter is software that constrains what kind of data ends up in the database and ensures that data means what it is supposed to. That software will be created by local teams that know the business and the data. They will use AI to write the software and test it. Will those teams be “developers”? It is probably semantics or a matter of degree. Half the people writing advanced Excel spreadsheets today should probably be considered developers really.

Mostly agree, even without a database-centered worldview.

Programming languages are languages to tell the computer what to do. In the beginning, people wrote in machine code. Then, high level languages like C and FORTRAN were invented. Since then we’ve been iterating on the high level language idea.

These LLM based tools seem to be a more abstract way of telling the computer what to do. And they really might, if they work out, be a jump similar to the low/high level split. Maybe in the future we’ll talk about low-level, high-level, and natural programming languages. The only awkwardness will be saying “I have to drop down to a high level language to really understand what the computer is doing.” But anyway, there were programmers on either side of that first split (way more after), if there’s another one I suspect there will still be programmers after.

Maybe, but it's the same argument trickling down. You'll need the CRUD-apps because you hired Cindy to press the button, and if shit goes pear-shaped, you can point to Cindy in the post-mortem. If it's some AI agent pressing the button to egress data from the database, and there's an anomaly, then it's a systemic failure at a macro level at that company, which is harder to write a press release about.

Many applications can and should be replaced by a prompt and a database. This is the nature of increased expressive and computational power. So many whip manufacturers are about to go out of business, especially those offering whips-as-a-service.

No, enterprise software is typically also risk management and compliance, domains where rules rule. Someone needs to sign off on the software being up to spec and taking responsibility for failures, that's something any submissive LLM is willing to do but can't.

At some point, I wonder if there will be advantageous for AI to just drop down directly into machine code, without any intermediate expression in higher-level languages. Greater efficiency?

Obviously, source allows human tuning, auditing, and so on. But taken at the limit, those aspects may eventually no longer be necessary. Just a riff here, as the thought just occurred.

In the past I've had a similar thought, what if the scheduler used by the kernel was an AI? better yet, if it is able to learn your usage patterns and schedule accordingly.

...which is a good thing. Software made by the people using it to better meet their specific needs is typically far better than software made to be a product, which also has to meet a bunch of extra requirements that the user doesn't care about.