101–110 of 448 posts
I don't blame people for responding to the title instead of the article, because the article itself doesn't bother to answer its own question.
AI makes the first 90% of writing an app super easy and the last 10% way harder because you have all the subtle issues of a big codebase but none of the familiarity. Most people give up there.
0. It runs way too fast and far ahead. You need to slow it down, force planning only and explicitly present a multi-step (i.e. numbered plan) and say "we'll do #1 first, then do the rest in future steps".
take-away: This is likely solved with experience and changing how I work - or maybe caring less? The problem is the model can produce much faster than you can consume, but it runs down dead ends that destroy YOUR context. I think if you were running a bunch of autonomous agents this would be less noticeable, but impact 1-3 negatively and get very expensive.
1. lots of "just plain wrong" details. You catch this developing or testing because it doesn't work, or you know from experience it's wrong just by looking at it. Or you've already corrected it and need to point out the previous context.
take-away: If you were vibe coding you'd solve all these eventually. Addressing #0 with "MORE AI" would probably help (i.e. AI to play/validate, etc).
2. Serious runtime issues that are not necessarily bugs. Examples: it made a lot of client-side API endpoints public that didn't even need to exist, or at least needed to be scoped to the current auth. It missed basic filtering and SQL clauses that constrained data. It hardcoded important data (but not necessarily secrets) like ports, etc. It made assumptions that worked fine in development but could be big issues in public.
take-away: AI starts to build traps here. Vibe coders are in big trouble because everything works but that's not really the end goal. Problems could range from 3am downtime call-outs to getting your infrastructure owned or data breaches. More serious: experienced devs who go all-in on autonomous coding might be three months from their last manual code review and be in the same position as a vibe coder. You'd need a week or more to onboard and figure out what was going on, and fix it, which is probably too late.
3. It made (at least) one huge architectural mistake (this is a pretty simple project so I'm not sure there's space for more). I saw it coming but kept going in the spirit of my experiment.
take-away: TBD. I'm going to try and use AI to refactor this, but it is non trivial. It could take as long as the initial app did to fix. If you followed the current pro-AI narrative you'd only notice it when your app started to intermittently fail - or you got you cloud provider's bill.
I've been vibe-coding a Plex music player app for MacOS and iOS. (I don't like PlexAmp) I've got to the point where they are the apps I use for listening to music. But they are really just in an alpha/beta state and I'm having a pretty hard time getting past that. The last few weeks have felt like I'm playing wack-a-mole with bugs and issues. It's definitely not at the point others will be willing to use it as their…
AI makes the first 90% of writing an app super easy and the last 10% way harder because you have all the subtle issues of a big codebase but none of the familiarity. Most people give up there.
I deleted vscode and replaced with a hyper personal dashboard that combines information from everywhere. I have a news feed, work tab for managing issues/PRs, markdown editor with folders, calendar, AI powered buttons all over the place (I click a button, it does something interesting with Claude code I can't do programmatically). Why don't I share it? Because it's highly personal, others would find it doesn't fit th…
This sounds chaotic and fun.
Yes, you do produce more code. But LoC produced is never a healthy metric. Reviewing the LLM generated code, polishing the result and getting it to production-level quality still very much requires a human-in-the-loop with dedicated time and effort.
On the other hand, people who vibe code and claims to be 10x productive, who produces numerous PRs with large diffs usually bog down the overall productivity of teams by requiring tenuous code reviews.
Some of us are forced to fast-track this review process so as to not slow down these "star developers" which leads to the slow erosion in overall code quality which in my opinion would more than offset the productivity gains from using the AI tools in the first place.
They're in the app stores. Apple's review times are skyrocketing at the moment due to the influx of new apps.