The issue I'm facing:
How to get better at rambling without getting worse at coding.
Because rambling is not coding, and coding is a matter of experience/practice as much as thinking.
This issue is not specific to AI:
You're good at boxing so you start to teach it. But the more you teach it the less you practice it. Your muscle memory fades, your reflexes decrease, your stamina vanishes and even if your knowledge of boxing remains intact and you become a good teacher, sooner or later you come to realize you're not a boxer anymore.
How to enjoy AI-assisted productivity without losing, focus capacity, language knowledge (and the architecture/performance/security knowledge it implies) among other things?
Very salient point. My take on this (and I know it’s not very popular on HN) is that trying to preserve every pre-AI coding skill is probably a fruitless endeavor.
AI-assisted coding is here and it’s not going anywhere. In the same way most modern software engineers aren’t writing assembly anymore, I don’t think future engineers will need to understand exactly how every part of a codebase works under the hood. It’s just another layer of abstraction.
Having said that, I do think knowledge of architecture/performance/security remains a pretty large part of prompting correctly, although more conceptually than actual implementation. As long as you’re still using those concepts in your prompting, you can keep that judgment sharp, even if some of the implementation fluency fades.
For example, with the boxing analogy, yes, you lose some boxing skills, but you’re also becoming a way better boxing coach by consistently teaching it. I think that’s the tradeoff.
This issue is not specific to AI: You're good at boxing so you start to teach it. But the more you teach it the less you practice it. Your muscle memory fades, your reflexes decrease, your stamina vanishes and even if your knowledge of boxing remains intact and you become a good teacher, sooner or later you come to realize you're not a boxer anymore.
How to enjoy AI-assisted productivity without losing, focus capacity, language knowledge (and the architecture/performance/security knowledge it implies) among other things?
AI-assisted coding is here and it’s not going anywhere. In the same way most modern software engineers aren’t writing assembly anymore, I don’t think future engineers will need to understand exactly how every part of a codebase works under the hood. It’s just another layer of abstraction.
Having said that, I do think knowledge of architecture/performance/security remains a pretty large part of prompting correctly, although more conceptually than actual implementation. As long as you’re still using those concepts in your prompting, you can keep that judgment sharp, even if some of the implementation fluency fades.
For example, with the boxing analogy, yes, you lose some boxing skills, but you’re also becoming a way better boxing coach by consistently teaching it. I think that’s the tradeoff.