The Pragmatic Engineer. @pragmaticengineer.com 路 Jan 5

How AI-assisted coding will change software engineering: hard truths. About how these AI tools really work and how they could be the start of the return of software, as a craft. Based on a guest post by @addyosmani.bsky.social. Read it here: newsletter.pragmaticengineer.com/p/how-ai-wil...

115 likes 6 replies

?

Replies

MaryanneConlin 路 Jan 6

This is spot on for any discipline: "AI tools help experienced DEVELOPERS more than beginners... AI is like having an eager junior DEVELOPER on your team. They can write CODE quickly, but need constant supervision & correction." I've referred to Claude as my *Recalcitrant Intern* numerous times! 馃檮

Tim Kraut 路 Jan 6

Another pattern that works really well is to use AI to explain code/tools. Have a library with some bad docs? AI can probably help to understand how it works - way faster than manually reading through the source code. Same for unfamiliar programming languages

baxate 路 Jan 5

I don't see the value in using an LLM to do something I already know how to do. As the article states, if I have to review and rewrite its output, I could have just done it properly myself. And I'm already fast at doing things I know how to do.

Mark Techson 路 Jan 5

馃搶

@jan-kaspar.bsky.social 路 Jan 6

The resistance to AI in coding reminds me of two major transitions in programming history. When assembly language first replaced machine code in the 1940s, programmers insisted 'if you can't write it in binary, you don't understand what you're doing.

David Kobia 路 Jan 5

Because AI IDE's can't currently hold the entire context of a large project in memory, it leads to incomplete understanding, strange bugs and functionality. I for one welcome our new overlords, but ceding full control to a moving context window is playing with fire.