Hacker News Reader

Comment by ChadMoran | Hacker News Reader

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".

View on HN

How is that a great prompt having it run for an hour without your input? Sounds like it’s just generating wasteful output.

It can be fixing unit tests and stuff for quite a while, but I usually find it cheats the goal when unattended.

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.

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.

I have not tested Claude Code but that's impressive because other agents get stuck long before that.

Takes proper prompt crafting but Claude Code is really impressive.

With 7 hour tasks it might become worthwhile to invest in a RAM-based local solution with DeepSeek Coder? I've heard that you can run it with 300-700GB. With such long tasks, Claude may run out of usage, right? So queueing it up on a local server may make sense? Always looking for an excuse to do things in-house, but it has to make sense :)

That clears up a lot for me. I don't think I've ever had it take for than a couple of minutes. If it takes more than a minute I usually freak out and press stop

I've used CC a lot and to great effect, but it never runs more than 10 mins (Opus). Completely independent for 60 min, sounds impressive. Can you share some insights on this? Really curious; I can also share recents prompts of mine.

"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"

Wow! I will try that. Really cool. Never tried the mythical sub-agent feature, not sure if it was really a thing due to the sparse docs. The "You are an expert software engineer" really helps? Probably good idea to mention "simple" because Claude sometimes settles for an overengineered solution.

> The "You are an expert software engineer" really helps?

Anecdata, but it weirdly helped me. Seemed BS for me until I tried.

Maybe because good code is contextual? Sample codes to explain concepts may be simpler than a production ready code. The model may have the capability to do both but can't properly disguished the correct thing to do.

I don't know.

Maybe it's not the "expert", but "software engineer" part that works? Essentially it's given a role. This constrains it a bit; e.g. it's not going to question the overall plan. Maybe this helps it take a subordinate position rather than an advisor or teacher. Which may help when there is a clear objective with clear boundaries laid out? Anyway, I will try myself and simply observe it if makes a difference.

Are there some good examples/wiki/knowledge base on how to do this? I'll read 2 competing theories on the same day so I'm kinda confused.

Reply on news.ycombinator.com