Comment by kypro
3 days ago
It's been interesting watching HN shift in my direction on this in recent weeks...
I had been saying since around summer of this year that coding agents were getting extremely good. The base model improvements were ok, but the agentic coding wrappers were basically game changers if you were using them right. Until recently they still felt very context limited, but the context problem increasingly feels like a solved problem.
I had some arguments on here in the summer about how it was stupid to hire junior devs at this point and how in a few years you probably wouldn't need senior devs for 90% of development tasks either. This was an aggressive prediction 6 months ago, but I think it's way too conservative now.
Today we have people at our company who have never written code building and shipping bespoke products. We've also started hiring people who can simply prove they can build products for us using AI in a single day. These are not software engineers because we are paying them wages no SWEs would accept, but it's still a decent wage for a 20 something year old without any real coding skills but who is interested in building stuff.
This is something I wouldn't have never of expected to be possible 6 months ago. In 6 months we've gone from senior developers writing ~50% of their code with AI, to just a handful of senior developers who now write close to 90% of their code with AI while they support a bunch of non-developers pumping out a steady stream of shippable products and features.
Software engineers and traditional software engineer is genuinely running on borrowed time right now. It's not that there will be no jobs for knowledgable software engineers in the coming years, but companies simply won't need many hotshot SWEs anymore. The companies that are hiring significant numbers of software engineers today simply can not have realised how much things have changed over just the last few months. Apart from the top 1-2% of talent I simply see no good reason to hire a SWE for anything anymore. And honestly outside of niche areas, anyone hand-cracking code today is a dinosaur... A good SWE today should see their job as simply reviewing code and prompting.
If you think that the quality of code LLMs produce today isn't up to scratch you've either not used the latest models and tools or you're using them wrong. That's not to say it's the best code – they still have a tendency to overcomplicate things in my opinion – but it's probably better than the average senior software engineer. And that's really all that matters.
I'm writing this because if you're reading this thinking we're basically still in 2024 with slightly better models and tooling you're just wrong and you're probably not prepared for what's coming.
Hi Kypro this is very interesting perspective. Can you reach out to me? I'd like to discuss what you're observing with you a bit in private as it relates heavily to a project I'm currently working on. My contact info is on my profile. Pls shoot me a connection request and just say you're kypro from HN :)
Or is there a good way for me to contact you? Your profile doesn't list anything and your handle doesn't seem to have much of an online footprint.
Lastly, I promise I'm not some weirdo, I'm a realperson™ -- just check my HN comment history. A lot of people in the AI community have met me in person and can confirm (swyx etc).
Look forward to chatting!
LLM's are good at making stuff from scratch and perfect when you don't have to worry about the codes future. 'Research' can be a great tool. But LLMs are horrible in big codebases and multiple micro services. Also at making decision, never let it make a decision for you. You need to know what's happening and you can't ship straight AI code. It can save time, but it's not a lot and it won't replace anyone.
Are you saying this from experience?
We have a large monorepo at my company. You're right that for adding entirely new core concepts to an existing codebase we wouldn't give an AI some vague requirements and ask it to build something – but we wouldn't do that for a human engineer either. Typically we would discuss as a team and then once we've agreed on technologies and an approach someone will implement it relying heavily on AI to write the actual code (because it's faster and generally won't add dumb bugs like typos or conditional logic error).
Almost everything else at this point can be done by AI. Some stuff requires a little support from human engineers, but honestly our main bottlenecks at this point is just QA and getting the infra to a place where we can rapidly ship stuff into production.
> You need to know what's happening and you can't ship straight AI code.
I think there is some truth to this. We are struggling to maintain a high-level understanding of the code as a team right now, not because there is no human that understands, but because 5 years ago our team would have probably been 10-20x larger given the amount we're shipping. So when one engineer leaves the company or goes on holiday we find we lose significantly more context of systems than you historically would with larger teams of engineers. Previously you might have had 2-3 engineers who had a deep understanding of a single system. Now we have maybe 1-2 engineers who need to maintain understanding of 5-6 systems.
That said, AI helps a lot with this. Asking AI to explain code and help me learn how it works means I can pick up new systems significantly quicker.
> Are you saying this from experience?
Yes. I mostly work on Quarkus microservices and use cursor with auto agent mode.
> we wouldn't give an AI some vague requirements and ask it to build something > we would discuss as a team
seems like a reasonable workflow. It's the polar opposite of what was written in the blog post. That is the usual, easy way people use agents and what I think is the wrong path. May I also ask what language and/or framework you work with where so much context works good enough?
> Asking AI to explain code and help me learn how it works means I can pick up new systems significantly quicker.
Summarization is generaly a great task for LLMs
> a steady stream of shippable products
Software/web meat shops have bean around since the dawn of the time.
I worked at McDonald's in my teens. One of the best managers I ever worked for was the manager at this store at this time(the owner rotated him between stores to help get things on track).
I'll never forget this one thing he said: "They have changed the Filet-O-Fish five times since I've been here, and each time it's become more profitable".
Congrats on making slop more profitable.