I’ve had a similar experience. I’ve been vibecoding a personal kanban app for myself. Claude practically one-shotted 90% of the core functionality (create boards, lanes, cards, etc.) in a single session. But after that I’ve now spent close to 30 hours planning and iterating on the remaining features and UI/UX tweaks to make the app actually work for me, and still, it doesn’t feel "ready" yet. That’s not to say it hasn’t sped up the process considerably; it would’ve taken me hours to achieve what Claude did in the first 10 minutes.
I've got a few projects I've generated, along with a wholly handwritten project started in Dec.
The difference I've noticed is that the act of actually typing out code made me backtrack a few times refining the possible solutions before even starting the integration tests, sometimes before even doing a compile.
When generating, the LLM never backtracked, even in the face of broken tests. It would proceed to continue band-aiding until everything passed. It would add special exceptions to general code instead of determining that the general rule should be refined or changed.
The reason that some devs are reporting 10x productivity is because a bunch of duct-taped, band-aided, instant-legacy code is acceptable. Others who dont see that level of productivity increase are spending time fixing the code to be something they can read.
Not sure yet if accepting the spaghetti is the right course. If future LLMs can understand this spaghetti then theres no point in good code. If we still need human coders, then the productivity increase is very small.
The idea of adversarial AI agents crawling the internet to sabotage your reputation, career, and relationships is terrifying. In retrospect, I'm glad I've been paranoid enough to never tie any of my online presence to my real name.
>With a 10x boost, if you give an engineer Claude Code, then once they’re fluent, their work stream will produce nine additional engineers’ worth of value.
I keep hearing about this 10x productivity, but where is it materializing? Most developers at my company use Claude Code, but we don't seem to be shipping new features at ten times the rate. In fact, tickets still take roughly the same amount of time to complete.
I'm seeing that some tickets are "finished" (i.e. ready for PR) more quickly, but they end up needing so many changes and to be re-reviewed so many times it takes longer than it ever did because someone is saying yes to the LLM instead of designing software. When it's clear your review comments are just going back into the maw of the LLM, I've given up trying to guide and now just outright suggest actually workable designs (taking more of my time too), and that merely cuts down the number of times it will come back for review again.
Nothing is more infuriating at work than when you say something to someone in a message or PR comment, and they just paste the LLM response back to you.
Wow, you still get responses? I usually get 3 or 4 more commits (I've seen some of these touch nothing but comments but have a typical LLM-brained commit message as if it actually changed the functionality the comments were about, and some which literally won't compile) and the comment marked as Resolved.
Same. When I’m visiting my parents, I sometimes check the Screen Time stats on my dad’s iPad. Consistently, he’s spending around 30 hours per week on YouTube. It has pretty much replaced TV for him.
I can hardly get my mother, father or in laws to look at us anymore when we visit, they just look at social media and sometimes comment on whatever they saw and share it with me, sometimes via a message too. It's weird but for us, it's been going on since FB and Pintrest but Instagram and TikTok have taken the addiction to new levels.
They basically wouldn't travel to anywhere quality, high speed internet isn't present.
