|
|
|
|
|
|
by malux85
469 days ago
|
|
|
One of the interesting things about LLM coding assistants is that the quality of the answer is significantly influenced by the communication skill of the programmer. Some of the juniors I mentor cannot formulate their questions clearly and as a result, get a poor answer. They don’t understand that an LLM will answer the question you ask, which might not be the global best solution, it’s just answering your question - and if you ask the question poorly (or worse - the wrong question) you’re going to get bad results. I have seen significant jumps in senior programmers capabilities, in some cases 20x, and when I see a junior or intermediate complaining about how useless LLM coding assistants are it always makes me very suspicious about the person, in that I think the problem is almost certainly their poor communication skills causing them to ask the wrong things. |
|
|
Another thing I've found is to actually engineer a solution - all the basic coding principles come into play, keeping code clean, cohesive and designing it to make testing easy. The human part of this is essential as AI has no barometer on when it's gone too far with abstraction or not far enough.
When code is broken up into good abstractions then the AI part of filling in the gaps is where you see a lot of the productivity increases. It's like filling water into an ice tray.