I'd rather read the prompt

Re:I'd rather read the prompt by jama211 on Sunday May 04, 2025 @10:14PM (#43891389)

Well… you’re forgetting the part where you can cut out the middleman. Currently a leader has to ask an engineer to build a system, and has to communicate effectively with the engineer until all of the novel details have been ironed out in the specification, and _y_ the engineer builds it.

In a world where the LLM can do the building, the engineer is no longer required.

[ Parent | on HN ]

Re:I'd rather read the prompt by empthought on Sunday May 04, 2025 @10:27PM (#43891452)

You just turned your leader into an engineer, is all.

[ Parent | on HN ]

Re:I'd rather read the prompt by gherkinnn on Monday May 05, 2025 @04:03AM (#43892825)

More often than not, the building is the easy part once the specifics are ironed out.

In my experience, an ideas leader (you know the type) will fail at telling a machine exactly what to do and get bored with the inevitable edge cases, computers saying no, and non-ideas drudgery. This is where I believe every no-code and low-code and WYSIWYG platform and now LLMs fall apart.

A major aspect of programming is translating the messy meatspace to something an extremely fast moron (a computer and I wish I coined this term) understands. And as much of a step change LLMs for writing code are, I have yet to see them take this step.

[ Parent | on HN ]

Re:I'd rather read the prompt by immibis on Monday May 05, 2025 @04:48AM (#43893043)

They've tried this before and they made COBOL. Turns out you still need programmers to write COBOL because it's still programming even if the program looks Englishy.

[ Parent | on HN ]