You can say this about every major invention. The loom destroyed jobs! The engine destroyed jobs! So on and so forth.
This view is critically flawed in two major ways:
1) AI is not anywhere near being able to replace the majority of what developers do on a product team. We are decades away from a PM at Facebook being able to type "make a twitter clone that uses instagram login and can scale to 1 billion" and have an AI just do it.
2) Programming and product work is not zero sum. The more we can do means the more product we can make. It means more products can be made overall. After the loom came out, we simply made more clothes than ever before and in the process created a ton of jobs. We are not at some peak software point where we've completely saturated all humanity's need for software or profitable software and thus tools that increase efficiency don't put us out of work.
And frankly, if we develop the kind of general AI that accept a query like "make a facebook competitor capable of scaling to 10 billion" and simply do it, inventing whatever languages, frameworks, hardware, processors, patterns, methodologies, global datacenters handling global politics and law, etc, etc necessary to accomplish such a task, then so be it. I welcome the overlords!
This view is critically flawed in two major ways:
1) AI is not anywhere near being able to replace the majority of what developers do on a product team. We are decades away from a PM at Facebook being able to type "make a twitter clone that uses instagram login and can scale to 1 billion" and have an AI just do it.
2) Programming and product work is not zero sum. The more we can do means the more product we can make. It means more products can be made overall. After the loom came out, we simply made more clothes than ever before and in the process created a ton of jobs. We are not at some peak software point where we've completely saturated all humanity's need for software or profitable software and thus tools that increase efficiency don't put us out of work.
And frankly, if we develop the kind of general AI that accept a query like "make a facebook competitor capable of scaling to 10 billion" and simply do it, inventing whatever languages, frameworks, hardware, processors, patterns, methodologies, global datacenters handling global politics and law, etc, etc necessary to accomplish such a task, then so be it. I welcome the overlords!