Hacker News Reader

Comment by donperignon | Hacker News Reader

Is not the first time that I read this kind of narrative, actually appears pretty often in my LinkedIn timeline. We are now managers of agents and now we are CTO of agents… this is plain delusional, you can play with the toys all day long, a mud cake won’t sell very well. This CTO doesn’t code much, I agree, if you are a contributor you know that so called agents are as useful as google and stack overflow on steroids, nothing more than that unless you have no idea of what you are doing.

View on HN

Agents are definitely more useful than Google and SO… have you tried pair programming with Claude 4 Opus and building something? It’s amazing.

I have, and it does a mediocre to poor job, even at trivial tasks using popular stacks and languages. IME, one most either start with a green field, or babysit every step with/as an expert, or both. Perhaps I've just been unlucky or my projects have too much debt.

I agree with the other reply. This is a tool like any other and it takes skill and practice to use it effectively. I'm learning how best to create and persist architectural guidance.

For example giving it a meta process to follow before making an edit. I've also had the models keep a document of architecture and architecture decisions.

I’ve used it greenfield and with existing indebted codebases and it’s remarkably good at both. You have to give it a good amount of context but that goes for a human worker too. I think devs who get bad results from AI generally prefer to be the ones coding and not managing and maybe take their own context for granted.

Most of my time spent coding is understanding and growing my context. By the time I’ve done that, writing the code is an afterthought. It takes longer to communicate this via prompt than to write the code myself.

I’ve heavily benefited from AI when I’m inexperienced or willing to trust the AI. The devs I’ve seen happy with AI either fit that use case or are subpar devs who don’t really understand what they’re doing. I have multiple coworkers who are the latter - code works for their single happy path and they’re on to the next thing.

You need to start with a green field as the LLM makes lots of assumptions about your code base, based on what it learned before. Doing it green field means less resistance from the LLM.

I think, based on that, Rust will be the most popular and powerful language by next year. Of course, I might be completely wrong.

Exactly. Having built a few non-trivial projects with Claude Code, you can act as a CTO. At least that is one semi feasible way of using it.

I would say in a generation or two, you could operate in a way where you rarely have to dive into the code.

I’ve been building a project in my spare time with CC and gotten at least 5x more done than I could have alone. Probably closer to 10. And it makes it easier to work when I’m kind of tired and would normally choose not to work on the project at all, because I can relax or do house chores while it crunches on a problem. It’s amazing.

> Having built a few non-trivial projects with Claude Code

Can you clarify what "non-trivial" means here? To me "non-trivial" is writing FoundationDB or Kafka from scratch.

That’s why I said it’s like it but on steroids. It is what is it’s.i didn’t try (insert here last hyped version of whatever) I tried the mainstream services and it’s definitely not like to be “a manager” or CTO of agents

Reply on news.ycombinator.com