Hacker News Reader

Comment by ridruejo | Hacker News Reader

[flagged]

No it doesn’t. It’s dead easy to get a decent level, and going further requires individual effort and skill—-just like any other field of endeavor.

Gatekeepers who claim otherwise have something to sell.

How can it be gatekeeping when they are literally making it easier to use? The analogy is probably closer to a Linux distro. You can put everything together yourself but if someone gives you a pre integrated environment with best practices it makes it easier to get started

How on earth does this compare to a Linux distro? What are you even talking about here?

I see a Linux distro as a collection of libraries that someone puts together following best practices and conventions (ie all config files go into /etc). The similarity with this project is that Microsoft has taken a collection of tools and best practices and put them together in an easy to install package

I find that analogy weak.

Picking a Linux distribution is a commitment, and if I want to change it out I have a lot of work to do, much of which is unwinding my own work that was distro dependent.

Changing out an agent setup is as easy as installing an IDE, and if I don’t like it I can go back easily. My work is not dependent on the setup - the value I get is transactional, and the quirks of each model or agent approach are not difficult to learn or live without.

All of which suggests that selling ease of use to someone like me will be pointless. I’m sure there are clueless F500 managers out there who might go for it. But a business model based on selling to people who don’t know anything isn’t very durable.

You may not be the target user for this project then and that’s fine! They are releasing this as a research project so a business model was not probably one of the key decision points.

Ah yes an easy to install package, totally the hallmark of your average Linux distro :)

Not sure if you are being serious or not. That was indeed the point of the very first Linux distros and why most people use them nowadays vs the alternative.

I started using Linux before there were distros (circa 1993) and it was not a pleasant experience compared to when Slackware came out

> A lot of developers either don’t use coding agents to their full potential

Define "full potential".

Sounds like you are just making things up to sell your product.

Our “product” is a tool we developed internally and found it so useful that decided to open source it.

With full potential I refer to getting the best possible results. For example, being able to work on tasks in parallel without Claude instances interfering with each other vs , well, no doing so.

Thanks for making it public. I love the zen architect. Will definitely try it.

We do Rover, which is different from the Microsoft product but the goal is similar. I was just responding to the above comment. I agree with you, it is a pretty good project and will be taking a look. We are so early there are tons of things to learn and try.

Common etiquette is to declare your conflicts of interest

Agreed, it is in my bio but I updated the post in any case

ah I just realize actually u are rover dev

I wonder why do you think we need rover? what is the use case? I got confused

before that we ask ai with a chat feature

the next we need a multiple swarm of ai why though?

The main use case why we developed Rover internally (and still is) was the ability to run agents in parallel. It allows us to go much faster but requires tooling around it.

Secondarily it makes it easier for everyone to share those best practices and tooling among us, but is less of an issue because we are a small team

Fwiw in my company there’s a lot of interest in sharing best practices but it seems the learning is not as portable as hoped. My view is that it’s a personal learning journey and smoothing that journey beyond a certain point turns into spoonfeeding and reduces learning effectiveness significantly. Give a man a fish, and so on.

Reply on news.ycombinator.com