Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Field Notes from Shipping Real Code with Claude

diwank.space

Post reply on HN
Print view View original

101–107 of 107 posts

Re: Field Notes from Shipping Real Code with Claude

#101

Post by ericb »

never_inline wrote: post #75
ericb wrote: post #67

Earlier quoted context omitted.

Is the percentage meaningful, though? If an LLM produces the most interesting, insightful, thought-provoking content of the day, isn't that what the best version of HN would be reading and commenting on? If I invent the wheel, and have an LLM write 90% of the article from bullet points and edit it down, don't we still want HN discussing the wheel? Not to say that the current generation of AI isn't often producing bor…

Because why do you anti-compress your thoughts using LLM at all? It makes things harder to read.

I re-compress my thoughts during editing. That's how I write normally. First, a long draft, then a short one. Saving writing time on the long draft is helpful.

Slop is slop, whether a human or AI wrote it--I don't want to read it. Great is great. Period. If a human or AI writes something great, I want to read it.

Assuming AI writing will remain slop is a bold assumption, even if it holds true for the next 24 hours.

“I didn't have time to write a short letter, so I wrote a long one instead.”

- Mark Twain

Re: Field Notes from Shipping Real Code with Claude

#102

Post by tinodb »

diwank wrote: post #26
kasey_junk wrote: post #2

One of the exciting things to me about the ai agents is how they push and allow you to build processes that we’ve always known were important but were frequently not prioritized in the face of shipping the system. You can use how uncomfortable you are with the ai doing something as a signal that you need to invest in systematic verification of that something. As a for instance in the link, the team could build a syst…

For sure. Another interesting trick I found to be surprisingly effective is to ask Claude Code to “Look around the codebase, and if something is confusing, or weird/counterintuitive — drop a AIDEV-QUESTION: … comment so I can document that bit of code and/or improve it”. We found some really gnarly things that had been forgotten in the codebase.

But why stick with the AIDEV- style? I mean, this is what comments are for: explaining the why that can’t be read from code. You could just make it a regular comment, right?

Re: Field Notes from Shipping Real Code with Claude

#103

Post by diwank »

tinodb wrote: post #102
diwank wrote: post #26

Earlier quoted context omitted.

For sure. Another interesting trick I found to be surprisingly effective is to ask Claude Code to “Look around the codebase, and if something is confusing, or weird/counterintuitive — drop a AIDEV-QUESTION: … comment so I can document that bit of code and/or improve it”. We found some really gnarly things that had been forgotten in the codebase.

But why stick with the AIDEV- style? I mean, this is what comments are for: explaining the why that can’t be read from code. You could just make it a regular comment, right?

yup but:

1. AIDEV-* is easier to visually distinguish, and

2. it is grep-able by the models, so they can "look around" the codebase in one glance

Re: Field Notes from Shipping Real Code with Claude

#104

Post by indigodaddy »

diwank wrote: post #95
panny wrote: post #80

Earlier quoted context omitted.

>Think of this post as your field guide to a new way of building software. By the time you finish reading, you’ll understand not just the how but the why behind AI-assisted development that actually works. Hi, AI skeptic with an open-mind here. How much will this cost me to try? I don't see that mentioned in your writeup.

There are a bunch of different options so it depends on the models you end up liking but the simplest place to start is to get Claude Max $100 tier and use Opus 4 (the others don’t really get you the full experience)

Isn't Claude Code fully functional/available now on the $20 Pro monthly plan?

Re: Field Notes from Shipping Real Code with Claude

#106

Post by diwank »

indigodaddy wrote: post #104
diwank wrote: post #95

Earlier quoted context omitted.

There are a bunch of different options so it depends on the models you end up liking but the simplest place to start is to get Claude Max $100 tier and use Opus 4 (the others don’t really get you the full experience)

Isn't Claude Code fully functional/available now on the $20 Pro monthly plan?

In my experience, you’ll run out of Opus usage credits way too quickly on the Pro plan
Post reply on HN