This post convinced me to go down the Claude Code Learning Curve.

Thanks for all the insights!

Posting my #ActiveReading notes below.

-–

Experience is an excellent school; unfortunately, the fees are very high.” Let me share the fruits of my experience so you don’t have to pay the high fees.

Loved this quote.

If Claude does something you don’t like, don’t just correct it once — ask it to update the CLAUDE.md file so it remembers for next time.

Honestly, I think this is one of those thigns develoeprs just need to “not be lazy about” to constantly take their personalized AI tooling to the next level

Reminds me of my short note on how to end every conversation thread with a Claude Project: https://olshansky.medium.com/how-you-should-end-every-claude-project-conversation-0a88c744ef0d

Perfect Your Code (Beyond Just Writing It)

tl;dr The essence of code maintainability.

1. Update docs

2. Write tests

3. Clarify comments

4. Improve readability

Going to try this out this week.

While working on documentation, I asked it to generate a diagram using GraphViz (dot).

This is where I have to be one of those people on the internet that have to disagree and povide their opinion.

🧜 diagrams all the way

I have a cautionary tale: I allowed Claude to do git adds, and it enthusiastically added ALL the files in a folder with a “git add .” — including some files with sensitive information. I had to pull the plug immediately, but I was too slow on the escape key.

This is great. We’re entering a world of of a new form of “bugs and issues” that we’ve never had to think about. Things that are more fun that just prompt injections.

When working on 3D modeling, I pulled the source for one of the big OpenSCAD libraries (BOSL2) into the directory. Claude could then grep through those files, search them, and learn from the existing code.

This is super interesting.

For the diagrams I mentioned above, I had Claude not only look at the DOT files, but also examine the PNG files generated from them to improve the visualizations.

The fact that mermaid diagrams are also structued, contextual and embdeedd in .md files, I see an opportunity here.

When I asked it to rewrite this article in my style, it sounded a lot more like me. Am I really that predictable?

The time to extract all my substack post, notes, medium comments, tweets, etc is coming!

It’s not expensive, but it is possible to rack up say $10 of tokens in a day, or $200 a month if used seriously

I wish it was included in the monthly subscription…

there’s a command line option called “ — enable-architect.”

#ProTip

The productivity gains are significant, but the real value comes from the mental bandwidth it frees up for the creative aspects of coding.

I believe this is why we’re actually having a resurgence in software engineering.

The last ten years were all about memorizing frameworks and boilerplate.

Now it’s all about thinking and having fun again.

The learning curve is worth climbing

You convinced me.