Hacker News Reader

Comment by sreekanth850 | Hacker News Reader

build this prototype from end-to-end, is this how people build serious software with AI?

You're not gonna get something that's ready to ship, but as a first pass to get something running yes. Let's you explore far more ideas with only a few hours of agent time.

And you can’t use deepseek with a loop approach for creating such PoCs?

You absolutely can. On a large codebase. Written in multiple languages. I also use gpt models and for most tasks I prefer ds. It can orchestrate really well, and it stays on task without going off to reinvent the w̵h̵e̵e̵l̵ state machine.

I started KeenLore (an emotive audiobook creator) that way. I gave it software specifications, languages, JSON schema definitions, container requirements, hardware configuration (8GB NVIDIA T1000 GPU, 96GB RAM), and zero user interface mockups. For the second round, I asked it to build a completely independent, re-entrant, and data isolated demo system on top of the web application. The demo application included voice generation using one of its voice designs. Here's the output:

https://www.youtube.com/watch?v=WAeHgE94rVo

The system performs quotation attribution on my local hardware for my near-future, hard sci-fi novel (having nearly 500 quotations) with over 97% accuracy.

The initial prototype was developed quite quickly, but numerous successive iterations were required to fix numerous gaffs by Opus 5 (because it doesn't actually _understand_ what it takes to make general-purpose audiobook narration software).

For a prototype or a 1 or 2 use tool, yes, this is exactly how serious people are building software.

This is how ChatGPT, Cursor apps are built. They spent so much money on PR stunts, but "thousands of agents" can't make an app that doesn't freeze on each keystroke. Not even talking about user-friendly ui

Weird, ChatGPT has always worked really well for me.

Early on their software was like this, the original ChatGPT desktop app was basically unusable and full of memory leaks that would tank the software. They’ve long since fixed that though

The new ChatGPT desktop app is a dumpster fire though, it can’t even scroll properly when streaming the answer.

Such issues are pretty common among people I talk to at least. I hear comments about it pretty often, both when it comes to ChatGPT and Claude.

For myself, with ChatGPT for example, it regularly gets extremely slow if there is a lot of text in a single conversation. Especially if I try to scroll up.

Some pages have been strangely just broken for a while now as well. Usage analytics just renders lots of these duplicate "Usage history" components, where the data just never loads: https://imgur.com/a/vpcQIiw.png

I can totally imagine a scenario where some agent built it, another tested and approved it, and nobody at OpenAI even looked at it once or knows that it's like this.

> it regularly gets extremely slow if there is a lot of text in a single conversation

Now this I have definitely experienced. I chalk that up to it being an electron app, but who knows.

We use codex in vscode. Use agentic development but, agents only do things that We agree upon. Like We create impact study, proposals, feasibility and then implementation plan with full regresison, test coverage and end to end smoke test. A new fetaure will be given to front end only if it satisfy all our requirement in real API smoke test. It is not fast. but still we think we get 10X productivity gains and clean code, consistant quality and maintainability. And we dont use AI for front end. We have also found C# is more effective for agentic development. With Roslyn APIs, strong typing, structured namespaces, and compiler level semantic information, agents can navigate and reason about the codebase with relatively little context. In our experience, C# is surprisingly token efficient for large codebases cmpared to Go or rust.

I don't think most prototypes are serious software.

Reply on news.ycombinator.com