That's because we've been here before. Be it the ERPs of the 90s-00s, the low/no-codes of the 2010s, the SaaS and the chatbots of 2015. There was always hype about automating the job. At the end of the day, most of a programmer's job is understanding the business domain, it's differences and edge cases, and translating those into code. An LLM can do the latter part, the same way a compiler can do high-level java into assembly
The leading coefficient of these tools successfully getting you to/near the goal is all about clearly articulating the domain and the job to be done
Ergo, it's pretty important to craft experiences that make their core mechanic about that. And that's how Copilot Workspace was designed. The LLM generating the code is in some ways the least interesting part of CW. The effort to understand how the code works, which files must be touched, how to make coordinated changes across the codebase — that's the real challenge tackled here.
But there is so much context that the LLM has no access to. Implicit assumptions in the system, undocumented workflows, hard edge cases, acceptable bugs and workarounds, Peter principle boundaries, etc... All these trade-offs need someone that understands the entire business domain, the imperfect users, the system' implementation and invariants, the company's politics and so much more. I have never encountered a single programmer, no matter intelligence and seniority, that could be onboarded on a project simply by looking at the code.
