Asking the LLM to 'just' fix 'it', or whatever, is going to get you lost in the woods.
You're car will have spun off the road and you'll find it harder and harder to control it and keep it on the road because you have less and less visibility into the vehicle, nor will you be able to clearly see out your windscreen to use the car and road metaphor. You'll be driving blind eventually, unless your working on some simple closed toy problems and/or other small systems.
Building large systems means understanding the system. Without understanding the system, you lose control of it.
The LLM can probably help you understand the system to gain/regain some control of it again, but now you're becoming a system specialist rather than someone who's repeating, "fix it" and "make it good" or whatever.
In a way, that’s the situation today. You can pay an experienced developer $$$$ to do it right, or you can outsource it and pay $$ but pay extra for more layers of review, have lots of unfixed bugs and more tech debt.
You are proposing that instead we pay the frontier model to clean it up. If it can, I expect it to cost somewhere in the neighborhood of an experienced dev because that’s the alternative. That’s the way the frontier AI companies will extracting the value of the work from you.
Asking the LLM to 'just' fix 'it', or whatever, is going to get you lost in the woods.
You're car will have spun off the road and you'll find it harder and harder to control it and keep it on the road because you have less and less visibility into the vehicle, nor will you be able to clearly see out your windscreen to use the car and road metaphor. You'll be driving blind eventually, unless your working on some simple closed toy problems and/or other small systems.
Building large systems means understanding the system. Without understanding the system, you lose control of it.
The LLM can probably help you understand the system to gain/regain some control of it again, but now you're becoming a system specialist rather than someone who's repeating, "fix it" and "make it good" or whatever.
well said. This is exactly why platforms selling vibecoding are scams.
Exactly.
In a way, that’s the situation today. You can pay an experienced developer $$$$ to do it right, or you can outsource it and pay $$ but pay extra for more layers of review, have lots of unfixed bugs and more tech debt.
You are proposing that instead we pay the frontier model to clean it up. If it can, I expect it to cost somewhere in the neighborhood of an experienced dev because that’s the alternative. That’s the way the frontier AI companies will extracting the value of the work from you.
> I expect it to cost somewhere in the neighborhood of an experienced dev because that’s the alternative
But there's two ways this could be true: Frontier models costs rise, or (more likely) experience dev costs fall
Opus on enterprise pricing is not exactly cheap.
In complex systems, issues keep piling up faster than you can fix them.