HN user

anditherobot

83 karma
Posts5
Comments44
View on HN

Microsoft’s biggest dev move would be to make one clear “default” stack for each app type: one for web, one for desktop, one for mobile.

They already have strong tools. Just way too many paths They should make the recommended stack obvious and well-supported.

Vibe coding sits on an axis from smart autocomplete to one-shotting a $1B SaaS. Traditional software engineering was about holding the system in your head and translating it into syntax, fighting tooling and architecture decisions along the way. I think done properly it removes many of these friction points along the way to validating / implementing the idea.

Now it's easier to traverse a live plan and to quickly make micro pivots as you go.

I also think that architecture needs to change. Design patterns that will help to provide as much context to the LLM as possible to increase understanding.

Fair challenge to the idea. But what i am saying is that every line of boilerplate, every import statement, every configuration file consumes precious tokens.

The more code, the more surface area the LLM needs to cover before understanding or implementing correctly.

Right now the solution to expensive token limits is the most token-efficient technology. let's reframe it better. Was react made to help humans organize code better or machines?

Is the High Code-to-Functionality Ratio 3 lines that do real work > 50 lines of setup really necessary?

We're overlooking a critical metric in AI-assisted development: Token and Context Window to Utility Ratio.

AI coding tools are burning massive token budgets on boilerplate thousands of tokens just to render simple interfaces.

Consider the token cost of "Hello World":

- Tkinter: `import tkinter as tk; tk.Button(text="Hello").pack()`

- React: 500MB of node_modules, and dependencies

Right now context windows token limits are finite and costly. What do you think?

My prediction is that tooling that manage token and context efficiency will become essential.

With Visual Studio and Copilot I like the fact that runs a comment and then can read the output back and then automatically continues based on the error message let's say there's a compilation error or a failed test case, It reads it and then feeds that back into the system automatically. Once the plan is satisfied, it marks it as completed

Microsoft Amplifier 9 months ago

Have you tried Scoped context packages? Basically for each task, I create a .md file that includes relevant file paths, the purpose of the task, key dependencies, a clear plan of action, and a test strategy. It’s like a mini local design doc. I found that it helps ground implementation and stabilizes the output of the agents.

How did people differentiate between 1 and L, 5 and S, 0 and O?

ex: 1055 & LOSS ( one zero five five & loss)

Meta 3D Gen 2 years ago

Can this potentially support :

- Image Input to 3D model Output

- 3D model(format) as Input

Question: What is the current state of the art commercially available product in that niche?

Once upon a time, we crammed HTML, CSS, and JavaScript into single PHP files—easy and straightforward. But then, someone said, "Separate presentation from logic!" So we did.

Then someone said, "Sending HTML is old news; let's send JSON on the back end and reassemble everything with JavaScript." So we did.

Then someone said, "Why don't we put everything in a single file and call them components?" So we did.

Then someone said, "Why don't we push those components from the server instead?" So we did

Wait a minute???

In a statically typed language and explicit type definitions.

int age = will never have string "December".

But in python both: age = 42 and age = "December" are possible.

I could be a new architecture.

A processor has different cores, Computers may have several hard-drives, 4 sticks of ram.

Each component can run in parallel.for example, if a long video processing task is underway and your text generation component is idle, it could assist.

Should the audio component fail , only that specific part would be affected.

Good point. And when you talk about a few years away this made me think about the ENIAC. A modern household typically consumes far less electricity than ENIAC.

Now our smartphones are 1000 times more powerful than the ENIAC and use less power.

Do you think Apple likes to jump on things? Apple usually tries not to be first, but definitely likes to polish .

Really! I always imagine a system: Composed of 5 specialized computers.

One for each category: audio, text, video, image.

One analyzer to coordinate everything.

This would be my API that I could access with mobile devices.

Here's a scenario:

I could talk to my phone about ideas, in the background it would create apps prototypes, create posters, make music based on something i whistle, teach me ask i ask question about a topic.

We could delegate the mundane stuff to it.

How far are we from having a consumer box that can run "AI"?

A computer like device that can "generate text", "generate audio", "generate video" and also "train".

Configure a PHP environment on your windows, mac or linux machine

Create index.php and put your content.

Link Jquery and Bootstrap/Bulma/Skeleton css framework

Start with the basics stuff and slowly increment, until you have a working prototype.

Start with the default PHP server: php -S localhost:8000

PHP is object oriented and have a ton of libraries for everything imaginable.

Discovering tribal knowledge. The frameworks provide a "framework", but the actual codebase is where the meat is. It's not just about knowing c# or PHP but learning the business, then how to solve the business problem with the technology.

For example. You have a flower delivery service. Programmers you understand flowers, types of packages, schedules, customer interactions will have an edge over everyone else.

PHP is amazing, yes the syntax is a little awkward. I love working with it.

Especially with libraries/ framework that are 10+ years old Their documentation is extremely detailed.

So you have more confidence that you'll deliver a working product. Instead of reading github issues to fix an obscure error message.

Old does not always mean outdated.