Human coders are still better than LLMs

Re:Human coders are still better than LLMs by hathawsh on Thursday May 29, 2025 @02:00PM (#44128526)

The difference is that when AI exhibits behavior like that, you can refine the AI or add more AI layers to correct it. For example, you might create a supervisor AI that evaluates when more requirements are needed before continuing to build, and a code review AI that triggers refinements automatically.

[ Parent | on HN ]

Re:Human coders are still better than LLMs by nevertoolate on Thursday May 29, 2025 @02:23PM (#44128753)

Question is, how autonomous decision making works, nobody argues that llm can finish any sentence, but can it push a red button?

[ Parent | on HN ]

Re:Human coders are still better than LLMs by johnecheck on Thursday May 29, 2025 @05:17PM (#44130477)

Of course it can push a red button. Trivially, with MCP.

Setting up a system to make decisions autonomous is technically easy. Ensuring that it makes the right decisions, though, is a far harder task.

[ Parent | on HN ]

Re:Human coders are still better than LLMs by malfist on Thursday May 29, 2025 @07:22PM (#44131328)

So it can push _a_ red button, but not necessarily the _right_ red button

[ Parent | on HN ]