Please change title, we don’t want clickbait here

What’s in this article is true, but to be honest I’ve never seen anyone using lines of code as an optimization metric. Even among the most AI enthusiastic people. I mean: the author of the article seem to be fighting non-existing problem.

You have 128GB of RAM

Who do you think I am, a multimilionaire?

Cloud. Windows is going to be sold as remotely accessible virtual machine hosted on Azure. The change will first take place in government offices, then in companies, and finally (after people get used to it at work) among consumers.

Why would gov and enterprise like it? Because of:

• safety - all enterprise data will be stored on Azure servers and won’t ever leave it. It makes preventing data leakage so much easier
• maintenance - software updates can be applied even outside of working hours, Microsoft could launch VMs and update at any time
• ease of upgrade - need better specs? you don’t need to buy better hardware anymore, you just buy better subscription. Hardware won’t become obsolete anymore that quickly

Consumers will also like it. No need to pay hundreds of dollars for new GPU when you just want to play newly released game. Also, all your data accessible from anywhere in the world.

And why Microsoft would like it? Kinda obvious, it would be even harder for users to quit a subscription, they will be tied to ecosystem even more

Yes, sounds ridiculous, but how will this ratio change if we take into account the cost of hiring a programmer and the costs of implementation of a niche feature that this experiment provides at a cost of LLM inference?

Also: we can cache and reuse enpoint implementation.

Kinda weird, Lemmy community is becoming more and more anti-everything recently 😂

I’m wondering what exactly caused so many downvotes? Isn’t video about updates to the most popular programming editor not suitable for community named “programming”?

Software you create with LLMs is deterministic, because it is the same code as you produce manually. The process of creating it is maybe not, but it is a task of a programmer to review it before publishing it.

AI is just an even higher level of abstraction. Just like we’ve replaced assembly with C (so we won’t need to know how processors work internally), and then C with some higher-level languages (so we could stop care about allocating memory that much), now we are replacing those higher-level languages with natural language (to stop wasting time on learning syntax of frameworks).

Does it mean programming jobs are obsolete? Of course not. Because programming was never about writing code. It has always been about translating requirements into actual software solutions.

I believe single binary compilation is not that uncommon these days. You can do that with Go or C#. Apart from obvious ones like c++.

I mean, I don’t want to discourage you, but from my experience choosing not popular language is not a good Idea if you want to actually accomplish something

What is your use case? Isn’t memory cheap nowadays?

I don’t think it has anything to do with vibe coding, the problem with MCP is just it needed to be done fast (because otherwise another protocol would appear and get all the hype) and needed to be very easy to use for hobbyists (again: to get hype, Enterprise software is boring)

All modern cars are either bloated/proprietery/unneccessarily complex. Pretty sure walking can do it all

What’s interesting is that people learning to code are more likely to say “I’m not using AI and I don’t plan to” then professionals.

Sounds counter intuitive to me because I expected professionals to be more conservative in that matter. They already have some habits developed, as opposed to new learners that in theory should benefit from AI because it makes doing simple things easier and can quite well explain basic concepts.

Everything comes down to proper function naming. If it wasn’t clear what function should return, then it was not named properly.