Comment by rahilb
11 days ago
> the cost of shipping code now approaches zero
Does anyone actually believe this is the case? I use LLMs to ‘write’ code every day, but it’s not the case for me; my job is just as difficult and other duties expand to fill the space left by Claude. Am I just bad at using the tools? Or stupid? Probably both but c’est la vie.
I feel I spend easily 3-5 times more on "QA" with LLM vibe coding than doing myself, the only difference, I couldn't code what I am currently making without LLM, the breath of knowledge required is just too vast.
Exactly the point I was going to make. Shipping something requires knowing how to ship it, monitor it, and fix it.
Writing code is the "easy" part and kind of always has been. No one triggers incidents from a PR that's been in review for too long.
LLM's can help with all of the above. Deployed an app with a backend, frontend, docker database and more with gitea on my NAS just yesterday. Have little knowledge about how it did it. Now I have a git remote to which I push and the app updates itself.
I guess it works well until you hit a stateful failure. My concern would be Day 2 operations—debugging a database issue or networking partition without a mental model of the underlying architecture seems pretty painful.
It would probably have been more accurate to say "the cost of writing code" -- and you're totally right about the rise of other duties (and technologies) that expand to fill that gap.
As a dev team, we've been exploring how we grapple with the cultural and workflow changes that arise as these tools improve--it's definitely an ongoing and constantly evolving conversation.
Same here. I use Claude Code everyday, very useful, but nowhere near to where I don't have to jump in and fix very simple stuff. I actually have a bug in an app that I don't fix because I use it as a test for LLM's and so far not one could solve it, it's a CSS bug!
I use Cursor daily, I have worked on Agents using LangChain. Maybe we are doing something wrong but even ysing SOTA models unless we explicitly give which mcp tool to call, it uses anything - sometimes - while other times it can do a passavle job. So now our mandate is to spell everything out to LLM so it doesn't add a non existent column like created at or updated at to our queries
I've used every SOTA for day to day work, and at best they save some effort. They can't do everything yet
Precisely, I always find myself thinking that maybe I'm just too dumb to use these LLM's properly, but that would defeat the purpose of them being useful haha.
1 reply →
I think the answer is that by the time AI can replace every function you do, it's also replaced everyone else and the world will either already have or will need to change radically.
I personally hope that the future becomes a UBI consumer-as-a-job thing, minus too much of the destructive impact that current consumerism has on the world.
Try to think logically. If AI eats all jobs, then nobody earns money any more to pay for everyone's UBI. The rich certainly won't do it.
Working together to make something is actually fun though. Seeing something you helped build be useful for others can be fulfilling. I'm not suggesting you should only live to work, but there are aspects of work that make life more enjoyable. I dread becoming a full-time consumer (aka retirement).
Of course it's the case. However, "shipping code" isn't valuable and never has been. Shipping the right code that actually works and actually solves a problem is what is valuable.
It's those who are shipping easily who are stupid. And what I mean by that is you can just ask the LLM to use the browser to get API keys and then use them to deploy. That's how the cost of shipping is zero. A hefty amount of YOLO code on top of YOLO deploy. I mean, you could also have the LLM build you a CI CD pipeline, but that's not YOLO.