All the excitement I felt because it was new to me, but it was really just a very basic toy not a real piece of software.
Meanwhile there were seasoned pros who could probably do amazing things even with GWBASIC. But that was more in spite of it than because of it.
this is the core issue. The best language we have for specifying this nuance is still programming languages, not English
Moving up from ASM -> C -> Python we're mainly abstracting over performance and implementation details, not functionality.
Here thouhg, in making the next jump from the high level Python to an English-specified LLM output we're trying to abstract over functionality. This doesn't work. It's flawed from the start
Vibe coding promises the world, and behold fails to deliver.
It sorta worked, and sorta didn’t. I’m seeing no evidence that this round is different. LLMs allow coding via natural language and assuming a lot of context that is typical to human conversation, but a lot of coding is delving into nuance, which is going to be work, no matter the tool.