The tooling around AI should be to improve the quality of the programmer. Not to write the code for the programmer.

For example if you ask an agent how to scale things well, and best practices in architecture, it will have a lot of resources on it. But that does not mean the code it will produce when you ask it to write a programme will consider and include the best practices it gave you in a separate question. That is the ‘intelligence’ part that LLMs cannot have. If you ask a it to do a certain way it will create it. Context tries to address this by prompting the user to give more, but that is not persistent.

This is exactly why senior devs finding LLMs works for them, because they know ‘how’ to do it, and they explicitly state it. But at the same time junior devs feel they think the code written by LLM is the ‘best’ way so solve a problem and superior in quality, even if it is not, because they don’t know any better.

Tooling should be able to help the developers improve their knowledge and skill on ‘how’ to do it. Instead it always focus on writing the code. I want to add that I’m not talking about algorithms. But every aspect of coding, in which the programmer needs to know ‘how’ to do it.

The biggest problem with this atleast for me is that I see people with decades of experience who still have awful taste.

They ran into an issue, learned either nothing Or the wrong thing from it and moved on.

Since the article mentions AI: I think good taste is to avoid LLM tools altogether. They hallucinate, seem to have provably no intelligence, and apparently frequently plagiarize. Then the junior coder in question wouldn’t need to wonder much about the LLM output quality either. There are enough reasons beyond the questionable quality to not use these tools.

Can be trained and not a gift, agree.

But just cos you got experience does not mean you got “it”.