Ask HN: Do AI coding tools make you a worse programmer?

I feel that for large basic scaffolding or a quick spin up of a framework or application structure is a great use of AI coding tools. Currently getting the tools to hold a lot of code in memory and extrapolate on the functionality tends to lead to a fall off of actually working code in my experience. I also know that using the tools to help solve a problem you are stuck on or something that you can not seem to get right is a good use. To prevent you from spending hours and hours trying to figure out something that a few prompts to an AI tool and some quick testing could figure out. IMHO I feel that current AI tools are great for moving things along in specific situations. Feeling like you're loosing your edge is natural when a tool comes along and shifts the way a job is completed. I feel that if you can understand the code the AI tool writes and you can test and implement the code then it's the same as having a someone else with more expierane write the code.

I had made the observation that I increasingly started to &quot;garbage collect&quot; all the small stuff that was basically akin to muscle memory.<p>To me it&#x27;s still worth it to keep up some level of &quot;language lawyering&quot; in my head as I had been practicing the craft of it all through daily application for many years. There was IMHO no reason to throw that away over time.<p>I only use LLMs for new stuff &#x2F; learning, though even there I&#x27;m still conflicted if reading the manual &#x2F; spec like we used to isn&#x27;t more efficient in the long run?<p>Again, retaining of basics &#x2F; primitives but also maybe better <i>mental modelling</i> by going deep head-first and on my own brain cycles?<p>TL;DR sharing the concerns; still conflicted in how useful LLMs are for programmers; maybe learning? Maybe interfacing for general utility outside of creative tasks is the main value? IDK...