But, as Cory puts it:
"""
It is nuts to deny the experiences these people are having. They're not vibe-coding mission-critical AWS modules. They're not generating tech debt at scale.
"""
I had a very visceral emotional reaction to this particular paragraph, and I find it very important to refute. Here are two points to consider:
1. YES THEY ARE.
They are vibe-coding mission-critical AWS modules. They are generating tech debt at scale. They don't THINK that that's what they're doing. Do you think most programmers conceive of their daily (non-LLM) activities as "putting in lots of bugs"? No, that is never what we say we're doing. Yet, we turn around, and there all the bugs are.
With LLMs, we can look at the mission-critical AWS modules and ask after the fact, were they vibe-coded? AWS says yes https://arstechnica.com/civis/threads/after-outages-amazon-to-make-senior-engineers-sign-off-on-ai-assisted-changes.1511983/
If you have a fediverse account, you can quote this note from your own instance. Search https://mastodon.social/users/glyph/statuses/116220325849374278 on your instance and quote it. (Note that quoting is not supported in Mastodon.)
RE: https://mastodon.social/@glyph/116220325849374278
Since I've gotten this feedback a couple times, I want to address it:
I know Cory is writing about *his specific* colleagues who he believes are using AI successfully, not devs in general, whose problems he has already implicitly acknowledged; I've moved the goalposts back to "developers in general".
That is, technically, an accurate description of what I did, but in the next post down in the thread, I explained *why*: I don't think his friends are special any more than mine are.
