I keep catching myself treating generation as the work.
The practice I would actually keep is writing three to five pass/fail checks before anything gets generated. If I cannot name those, I am not ready to hit go. Twenty-two pages is what you get after skipping that step and still calling it strategy.
Hey - part of this post doesn’t make sense. You’re saying don’t put out AI crap - sensible argument. But from there on you diverge and say that for content you have to write it yourself and get AI to polish it. And for code the other way around; which doesn’t make sense. A crap article is very similar with a crap piece of software from that perspective - things people don’t want to read/use cause they don’t make sense. So the method doesn’t really matter.
Totally fair. Code is a bit different because it's behind the scenes. The software can't be crap itself: it has to work, work well, be performant, etc. Admittedly crappy code makes it tough for developers to then understand it, and add to it, so it definitely has a cost, but it's different from content that's intent is to be readable & digestible.
There is some nuance here. While there may be objective standards for "good writing", I would put forward that there are more solid, universally agreeable standards for quality code. (e.g. It is a more structured problem space). Ignoring esoteric debates around coding languages and conventions. Code needs to solve a clearly identified problem (perhaps this is still the human input part . . . product vision and tradeoffs we are willing to live with). But when it comes to generation, test writing, refactoring old/legacy code, bug prevention / remediation, today's AI is more than sufficient IMO. (Note there may be other areas where humans are best, but this is a rapidly evolving space . . . system architecture to support scaling, specialized/nuanced code review, security/privacy ethics/tradeoffs.
I keep catching myself treating generation as the work.
The practice I would actually keep is writing three to five pass/fail checks before anything gets generated. If I cannot name those, I am not ready to hit go. Twenty-two pages is what you get after skipping that step and still calling it strategy.
Hey - part of this post doesn’t make sense. You’re saying don’t put out AI crap - sensible argument. But from there on you diverge and say that for content you have to write it yourself and get AI to polish it. And for code the other way around; which doesn’t make sense. A crap article is very similar with a crap piece of software from that perspective - things people don’t want to read/use cause they don’t make sense. So the method doesn’t really matter.
Totally fair. Code is a bit different because it's behind the scenes. The software can't be crap itself: it has to work, work well, be performant, etc. Admittedly crappy code makes it tough for developers to then understand it, and add to it, so it definitely has a cost, but it's different from content that's intent is to be readable & digestible.
There is some nuance here. While there may be objective standards for "good writing", I would put forward that there are more solid, universally agreeable standards for quality code. (e.g. It is a more structured problem space). Ignoring esoteric debates around coding languages and conventions. Code needs to solve a clearly identified problem (perhaps this is still the human input part . . . product vision and tradeoffs we are willing to live with). But when it comes to generation, test writing, refactoring old/legacy code, bug prevention / remediation, today's AI is more than sufficient IMO. (Note there may be other areas where humans are best, but this is a rapidly evolving space . . . system architecture to support scaling, specialized/nuanced code review, security/privacy ethics/tradeoffs.