Infrastructure management mostly — cron scheduling, DB migrations, nginx configs, log analysis. Things I know how to do but that are slow to type out.
But the learning is there:
I've used it to go deep on PostgreSQL query planning and indexing in a way I wouldn't have bothered with before.
The risk, in my opinion was the opposite of I'd expected — not learning less, but a lot of shallow things giving an impression of learning which in effect isnt there.
Look! i built this powerful thing. 60.000 Lines of coded business logic in a week!
On the surface i have something impressive to show. People admire it, and i end up believing that i did it. This is not to say that i did not learn - i did, but my learning was not as impressive as the result would make you believe.
I use Claude Code for basically everything around my product, not just the code itself:
- SEO audits (checking structured data, hreflang across 25 language versions)
- Batch blog translations (40 articles × 25 languages)
- Performance debugging (found that our entire SSR body was empty, LazyAuthProvider with ssr:false was wrapping all content)
- Admin dashboard analytics queries
The biggest unlock was giving it a good CLAUDE.md with workflow rules. It stops asking permission and starts fixing things autonomously.
Building a browser-based file tools product and CC handles probably 80% of the iteration cycle at this point.
It has been interesting to use in genealogy. Input known facts about an individual and it can quickly characterize much about that person: religion, diet, work, beliefs, aspirations & fears. You can discover how names evolved, learned which places they really called home, and where they were just passing through. Contextualizing this in wider known historical data (wars, treaties) can be immensely insightful.
I never gave a thought to the Thirty Years War only to find later it was necessary for my existence. And all the invasions of Ireland, from the Danes to Cromwell. And the expulsion of the Acadians in Canada. And cousin-lovin. It’s the last rabbit hole you’ll ever need to descend…
I find it great for nutrition and cooking. I used AI to build a food tracker that works at the micronutrient level (LLMs built the code but are mostly not used in the app itself) but many of my prompts are helping me to learn nutrition in general.
I also use it to help me learn to cook more/better so I ask it questions about the how / why and have made a database of recipes that I tweak based on interests / abilities.
A neat thing is you can always ask AI - what can I do to eat or cook better? Then you do it and keep repeating.
Infrastructure management mostly — cron scheduling, DB migrations, nginx configs, log analysis. Things I know how to do but that are slow to type out. But the learning is there: I've used it to go deep on PostgreSQL query planning and indexing in a way I wouldn't have bothered with before.
The risk, in my opinion was the opposite of I'd expected — not learning less, but a lot of shallow things giving an impression of learning which in effect isnt there. Look! i built this powerful thing. 60.000 Lines of coded business logic in a week! On the surface i have something impressive to show. People admire it, and i end up believing that i did it. This is not to say that i did not learn - i did, but my learning was not as impressive as the result would make you believe.
Maybe i should try using it to learning Math now.
I use Claude Code for basically everything around my product, not just the code itself:
- SEO audits (checking structured data, hreflang across 25 language versions) - Batch blog translations (40 articles × 25 languages) - Performance debugging (found that our entire SSR body was empty, LazyAuthProvider with ssr:false was wrapping all content) - Admin dashboard analytics queries
The biggest unlock was giving it a good CLAUDE.md with workflow rules. It stops asking permission and starts fixing things autonomously.
Building a browser-based file tools product and CC handles probably 80% of the iteration cycle at this point.
Could you refrain from using it for HN comments?
> Don't post generated comments or AI-edited comments. HN is for conversation between humans.
https://news.ycombinator.com/newsguidelines.html
It has been interesting to use in genealogy. Input known facts about an individual and it can quickly characterize much about that person: religion, diet, work, beliefs, aspirations & fears. You can discover how names evolved, learned which places they really called home, and where they were just passing through. Contextualizing this in wider known historical data (wars, treaties) can be immensely insightful.
I never gave a thought to the Thirty Years War only to find later it was necessary for my existence. And all the invasions of Ireland, from the Danes to Cromwell. And the expulsion of the Acadians in Canada. And cousin-lovin. It’s the last rabbit hole you’ll ever need to descend…
git clone the source code, then go to the directory where the program is located, and run a ai agent directly, eg codex， analyze and optimize the src
I find it great for nutrition and cooking. I used AI to build a food tracker that works at the micronutrient level (LLMs built the code but are mostly not used in the app itself) but many of my prompts are helping me to learn nutrition in general.
I also use it to help me learn to cook more/better so I ask it questions about the how / why and have made a database of recipes that I tweak based on interests / abilities.
A neat thing is you can always ask AI - what can I do to eat or cook better? Then you do it and keep repeating.