HACKER Q&A
📣 rdrmc

How are you preserving your skills while using AI?


I'm a senior engineer at [Big Company], and AI tools are ever-present. There's no mandate that you need to use them, but they are so readily available that most people do anyways.

There's a lot of society level concerns with AI, but on a personal level, I'm starting to slowly feel less skilled than I used to be. I can certainly do more, but I understand less. The "Prompt-Then-Review" loop of coding harnesses (Claude Code, Codex, Pi, OpenCode, Amp, etc.) just simply do not encourage mastery in the same way as shaping the code yourself. Sure, you can argue you're "thinking at a higher abstraction". But what happens when that abstraction fails? as abstractions often do.

It's not a fast process this skill erasure. I'm not magically losing my ability to code overnight. However, it feels like rust. Slowly eroding the pillars until they give.

This tool (currently) needs a skilled hand to guide correctly. However using the tool feels like it degrades the skilled hand. This negative feedback loop I find truly concerning from both the ability to make a living in software and the ramifications on software quality writ large.

So, I ask HN. How is the community protecting their skills? especially when actively using AI.


  👤 techblueberry Accepted Answer ✓
I’m in this exercise right now, and I’m thinking about, how do I stay in the drivers seat. I think it’s a version of, bionics not robots.

Im trying to go back in time to when AI was more autocomplete than agent and write my code with assistance. Find the file, find where the code goes autocomplete the fix. Rather than one shot multi file changes do one at a time.

The bosses probably don’t want people spending 4 hours figuring out why upgrading a package conflicted with another package in weird ways or changed the API or other obscure things, so like, give troubleshooting 10 minutes, try to grok the code context, then prompt for a fix. Or prompt “show me where I need to look to fix this” and fix it yourself.


👤 variety8675
I just don’t use any AI tooling for my home projects. Work pays for results so AI is basically mandatory to meet the deadlines - but home is for fun so I can take longer to produce hand crafted code.

👤 verdverm
> But what happens when that abstraction fails? as abstractions often do

One of the upsides to agents is that you can try out several abstractions instead of just one. You should absolutely be reading / spot checking the output (depending on context).

While skill loss is often the focus, there is also skill gain. I have learned new coding patterns or framework features through these tools.

On you main question, effort. Like everything, you have to use it or you lose it. I never saw my skill as a developer being the part where I peck at keys. It's the thinking and designing process, which I get to do way more of now that I don't have to peck.

Recommendation: build greenfield side projects, exercise building out all the parts. This will make you better at both being a developer and an agent manager.