ChadMoran

Still need good taste and judgement to build the thing people actually want to use.

I only started charging customers in September. Super-linear growth. I launched annual subscriptions and within less than a week > 15% of customers switched.

I'm noticeably faster shipping.

Understanding when to make something deterministic and not is critical. Taste and judgement is critical.

The only thing the comments told me is that people lake judgement and taste to do it themselves. It's not hard, identify a problem that's niche enough for a problem you can solve.

Stop arguing on HN and get to building.

Legitimately am. I get daily emails from customers telling me how much they love my product. Go search Google, it's free.

Search for "Rivian Roamer".

It's not an argument, it's a fact.

AI is an effort leverage tool, not a thinking one.

If you know what you're doing it can truly accelerate your work.

I definitely don't AI-generate all of the things.

For me it's a bandwidth increaser for the tedious parts.

I agree.

None of mine are vibe-coded. They're making a competent engineer like myself - more efficient.

The roadblock for me is the coding part, not the idea part.

I've launched 3 Rails SaaS products in the last 6 months, all profitable. In the world of LLMs things like this feel less valuable. I can kick off a Claude Code prompt and in 1 hour have a decent design system with Rails components.

Things like this likely need to be AI-first moving forward. This feels built for humans.

This is how I say it in my head.

Interesting take. As a low vision person, the icons help me scan menus like this.

It doesn't reliably do it. You need to inject context into the prompt to instruct the LLM to use tools/kb/etc. It isn't deterministic of when/if it will follow-through.

This is what holds me back from Zed.

This is the crux of knowledge/tool enrichment in LLMs. The idea that we can have knowledge bases and LLMs will know WHEN to use them is a bit of a pipe dream right now.

Sub-agents. I've had Claude Code run a prompt for hours on end.

Claude Code with a good prompt can run for hours.

Okay but when will we get visibility into this other than we're at the 50% of the limit? If you're going to introduce week long limits, transparency into use is critical.

This. Optimize for the good actors, not the bad ones.

"You are an expert software engineer

Your key objective is to fix a bug in the XYAZ class. Use a team of experts as sub-agents to complete the analysis, debugging and triage work for you. Delegate to them, you are the manager and orchestrator of this work.

As you delegate work, review and approve/reject their work as needed. Continue to refine until you are confident you have found a simple and robust fix"

Takes proper prompt crafting but Claude Code is really impressive.

You should really read this.

https://www.anthropic.com/news/claude-4

It was given a task and it solved a problem by operating for 7 hours straight.

Who said it was writing code for an hour? Solving complex problems by problem solving, writing SQL, querying data, analyzing data. formulating plans.

What do you do for hours?

If all you're thinking about is code output, you're thinking too small.

If you aren't hitting the limits you aren't writing great prompts. I can write a prompt and have it go off and work for about an hour and hit the limit. You can have it launch sub-agents, parallelize work and autonomously operate for long periods of time.

Think beyond just saying "do this one thing".

> The non-dev doesn't need to know/care.

Yes, they do. Context can't be all-compassing of everything that must be done.

Found it!

https://news.ycombinator.com/item?id=44064082

Run claude cli from inside of VS Code terminal.

https://news.ycombinator.com/item?id=44064082

Thank you!

I've been looking for that as well.