AI Assisted Coding

@stevelinz said in GAME CHANGE: A good practice is to zip up your project periodically, A better practice is to not rely on AI. I admit that the pull is strong, but resist and learn how to actually write your own code. I've been coding for over 45 years. That's right - when I started, I had to find a book that described the language I was using, and had to gleen knowledge without even having the luxury of example code. I think programmers have it way too easy nowadays. (I had to code uphill - BOTH WAYS! - when I was your age.) :) I tried AI a few times, and in the process of tailoring my prompt, I found that the AI becomes highly sycophantic, essentially claiming that I'm brilliant because I was able to craft an "awesome" prompt. I tried it yesterday, and told it what I was using (React v19 with typescript), and I actually had to tell it to maintain as much type safety as possible. Even so, if wouldn't give me const functions until I told it to, despite the fact that pretty much everyone that uses typescript in React uses const functions. I haven't looked at the code it churned out yet, because it was just a test to see how it would do, and I already have a solution that I wrote myself. I certainly wouldn't have it write an entire application.

@pkfox said in I signed up for Anthropic's Claude model - might go with Kagi's Claude next. Some observations: Hi HTCW, I recently used ChatGP to help me to convert/rewrite an MVC site to Blazor Server and I must say it was very helpful but as you say you have to watch what it gives you carefully - if you tell it exactly what you don't want it actually will improve its offerings - nice to see old names appearing here I've spent several weeks experimenting with AI vibe coding and have learned that it is good a small tasks but can't keep focus on larger tasks. You can constrain it through tracking and guidance documents (microsoft vs & vs code call them copilot-instructions.txt). The current issue is 2 fold: Constraints and guidance turn into hundreds of lines of input. How much each AI agent can remember before forgetting. A lot gets lost when they summarise. So, the further into the prompt they go, the less they remember, the more they improvise, and you lose a lot of control. So here is an example with Claude Sonnet 4, the best of the AI models at the moment: I have a library that I wrote recently called Blazing.Mediator. I used the docs as a guide that I gave to the AI. Everything starts well. However, if I let it run for a while and there is one or more summarisations, Claude switches to coding MediatR patterns. Overly opinionated! Then there is the cost... I find that I spend a lot of time cleaning up after the AI and lose any gains made if I let it loose on my code, adding new features. I now keep it to simple or repetitive tasks - wire-framing, prototyping, initial UI, comments, converting code, fixing errors/warnings, rubber ducking, etc... There are some things that it can do quicker than you without giving you work.