561–570 of 657 posts
Earlier quoted context omitted.
100k DAU - you’ll lose 98% within 6-9 months once 1-2 person team clones it as sells it for 10% of what you are charging
That was always a possiblty even before AI, what's hard to clone is how they got those users
funny the manager thought they could shoot from the hip like that. wonder if they think its an effective pattern
(edit: grammer)
Haven't seen this mentioned yet, but the worst part for me is that a lot of management LOVES to use Claude to generate 50 page design documents, PRDs, etc., and send them to us to "please review as soon as you can". Nobody reads it, not even the people making it. I'm watching some employees just generate endless slide decks of nonsense and then waffle when asked any specific questions. If any of that is read, it is b…
I've been tasked with code reviews of Claude chat bot written code (not Claude code that has RAG and can browse the file system). It always lacks any understanding of our problem area, 75% of the time it only works for a specific scenario (the prompted case), and almost 100% of the time, when I comment about this, I'm told to take it over and make it work... and to use Claude. I've kind of decided this is my last job…
I do not like the current culture around LLMs. I do not use LLMs, I shall continue to resist any peer pressure to use them, much as I have resisted IDEs in favour of CLI tooling, vim, tmux and the like. I feel my output is incredibly devalued compared to the before times.
On the one hand, my passion for personal projects has never been greater. It helps me feel as though I am bettering myself, pushing the boundaries of my capabilities without resorting to LLM usage. However, I no longer release my code openly.
On the other hand, on top of building resentment towards being treated even more interchangeably than before, I resent the asymmetry of my LLM-using peers submitting large pull requests I am obliged to review, on codebases I have never touched before, applications I have never had the occasion to use; my team is managed in such a way that everybody is more or less working on independent projects, due to pressures to deliver at a much faster pace.
I really wish the fervour would die down for the sake of my own sanity.
Before the advent of widespread LLM usage, and more particularly, before LLM-using coworkers began submitting large PRs against codebases I am the primary maintainer of, my velocity had never been greater. I do not like the current culture around LLMs. I do not use LLMs, I shall continue to resist any peer pressure to use them, much as I have resisted IDEs in favour of CLI tooling, vim, tmux and the like. I feel my o…
But man, people really oversell LLM's coding capabilities. It is good at pattern matching and replicating elsewhere. That's about it.
I had asked a simple question to opus 4.5.
> Python redis asyncio sample code.
The 3 attempts at generation all failed at the import statement. I verified if such an import structure ever existed in older versions. Never. But it looked convincing enough though!?
Is it because there is not much asyncio code (2014) is available for claude to train on?
So far this year I’ve realized I’m better of not using it except for simple questions I would otherwise google. Not necessarily because it’s bad but because it makes me worse.
Edit: this also sort of applies to my side projects as well. I’m realizing more the value of side project wasn’t the end result ( since those are mostly my own personal apps ) but the learnings gleaned from them I don’t get if I use Claude code.
Personally, mostly just using it for personal projects that I've been sitting on for years... it's been pretty motivating and I'm actually making progress, though I'm split across half a dozen things so it's slower going. I'm also far more interactive than vibe coding one and done efforts. I'm finicky when it comes to UX for user facing apps, and DevEx for developer APIs on libraries I work on.
It's nice, far from perfect... I still liken it to managing foreign developer teams... the more you specify ahead of time, the better the results. The difference is a turn around in minutes instead of the next business day. Iteration is very fast by comparison. That said, sometimes the agent will make toddler decisions like rewriting all the broken tests and updating the docs to match the behavior instead of correcting the behavior to match the api and tests.
Earlier quoted context omitted.
If what you are doing is novel then I don't think yolo'ing it will help either. Agents don't do novel. I've even noticed this in meeting summaries produced by AI: A prioritisation meeting? AI's summary is concise, accurate, useful. A software algorithm design meeting, trying to solve a domain-specific issue? AI did not understand a word of what we discussed and the summary is completely garbled rubbish. If all you're…
I’m a UX designer not a coder, but this is so bizarre to me because shouldn’t every project be doing something novel? Otherwise why does it exist? If this industry is so full of people independently writing the same stuff that AI can replicate it…then it was a vast misallocation of resources to begin with.