Sheeny96

What are we to believe this is some sort of, snort heh* magic iPhone or something?

Forgive my naive understanding of LLMs - but how do you get semantic understanding of a codebase, such that it knows what changes to make/why/where, without a wider understanding of language more broadly?

I'm using the word understanding loosely there, but I couldn't think of another word.

Idk about that, a company like Form3, Edenred etc are technically just software companies - but no one in their right mind is going to build a black box payment provider. Sure, if your business is wordpress websites, you're probably going to see a big downswing in new customers. But there is absolutely still going to be a place for highly specialised and security dependent software.

Design is functionality

> Improve SEO

> Reduce maintenance overhead

> Make your application compile faster

> Find unused code in our web app. Exclude generated files and test fixtures, and check for indirect references before recommending a removal.

If someone came to me with these requirements, I would laugh in their face. These reek of busy work with no actual business benefit. Have these people actually built real software before?

Why are the cars so big? Wouldn't it make sense to have a bunch of much smaller, single person vehicles?

How long ago did you use the tooling? I've seen this take a lot, and I can understand it if you're looking at the output of Sonnet 3.5 copy and pasted. But models like Opus 4.8, that just is not the case. Sure, you can't just whack it into the codebase, it needs review. But lets not pretend that 85% of programming jobs are CRUD with some async messaging. And the newer models are perfectly serviceable for that sort of work.

Yeah bro like why would you just build what you want to your vision? Other people don't want that! Other people know what they want, just build what they want!

I disagree, this read very non-AI prose to me. No "its not x - it's y", or em dashes etc.

We had this at my old work, except it wasn't a display, it was a circular piece of paper with "clean" on one side and "dirty" on the other. When it was done, you rotate the paper so it was clean side up. Should we have gone for series A? It was a pretty great MVP after all, albeit manual, but automation of the paper flipping would of course come on the second iteration

The problem with this is the reason LLMs are so good at writing Python/Java/JavaScript is that they've been trained on a metric ton of code in those languages, have seen the good the bad and the ugly and been tuned to the good. A new language would be training from scratch and if we're introducing new paradigms that are 'good for LLMs but bad for humans' means humans will struggle to write good code in it, making the training process harder. Even worse, say you get a year and 500 features into that repo and the LLM starts going rogue - who's gonna debug that?

I worked very hard for the first 5 or 6 years of my career - hit senior dev pretty quick, managed to double my pay moving into consultancy, and back on product dev in a smaller company nowadays.

Honestly? I don't feel a massive need to grow beyond where I am. I earn in the top 5% in my country. I live a comfortable and flexible life. I continue to learn like any dev with a passion for technology does - but i'm not constructing my life around an endless climb. If my role naturally transitions upwardly, great. If I stay where I am, steadily taking on more responsibility,that's also totally fine. The diminishing returns of chasing a CTO title or another arbritrarily large sum of money just doesn't seem worth it.