New post: AI-Assisted Coding on a Budget
Not vibe coding. Reading every diff. Writing tests. Shipping faster anyway. Also: the economics of inference and who gets left out.
https://agingcoder.com/posts/ai-assisted-coding-on-a-budget/
@ksoncan34
- 3 Followers
- 89 Following
- 27 Posts
Full stack and mobile developer interested in the challenges of our mobile future.
AI coding agents are powerful, but they don’t magically remove the need for:
• code review
• tests
• discipline
• skepticism
My review of Vibe Coding reflects on where the book gets this right — and where it falls short, especially when moving beyond solo projects into production systems.
Read here: https://agingcoder.com/posts/book-review-vibe-coding/
New post: I revisited React Native in 2025 after 8 years.
I built an app with React Native and… it mostly just worked.
What’s improved, what still hurts, and when I’d now recommend RN for new apps:
https://agingcoder.com/posts/looking-at-react-native-in-2025/
New blog post: RAG Time — Cooking Up Smart Recipe Suggestions with AI
Used a recipe database + embeddings + cosine similarity to build a FastAPI service that suggests recipes from your leftover ingredients.
A tasty intro to RAG (Retrieval-Augmented Generation).
Read here: https://agingcoder.com/posts/rag-time-cooking-up-smart-recipe-suggestions/
RAG Time: Cooking Up Smart Recipe Suggestions with AI and a Dash of Retrieval
This article explores how Retrieval Augmented Generation (RAG) can be used with large language models to suggest recipes based on user-provided ingredients. It walks through building a recipe recommendation system using embeddings, vector search, and prompt engineering, complete with code examples and a simple web interface.
Continuing my series on recipes + ML: last time was about clustering with unsupervised learning, this time it’s about serving those results in practice.
I show how to wrap embeddings + similarity search in a FastAPI endpoint, making recipe recommendations available as an API.
If you enjoyed the clustering post, this is the natural next step:
https://agingcoder.com/posts/2025-08-30-serving-the-cookbook-creating-an-endpoint-for-recipe-recommendations/
Continuing my machine-learning series—this time on unsupervised learning. The post walks through cleaning ingredients, building vectors, choosing K, clustering, and retrieving similar dishes.
https://agingcoder.com/posts/2025-08-25-clustering-the-cookbook-a-taste-of-unsupervised-learning/
Part 3 of my Supervised Learning series is LIVE!
How do you take a naive model and tune it into something nearly production-ready?
Find out in my latest deep dive with real scikit-learn code & tips:
🔗 https://agingcoder.com/posts/2025-06-23-experiments-in-supervised-learning-part-3/
#MachineLearning #scikitlearn #AI #Python
How do you take a naive model and tune it into something nearly production-ready?
Find out in my latest deep dive with real scikit-learn code & tips:
🔗 https://agingcoder.com/posts/2025-06-23-experiments-in-supervised-learning-part-3/
#MachineLearning #scikitlearn #AI #Python
I've written a fairly technical blog (and have already published the first 2 of at least 4 parts) on Supervised Learning. You can read all about it, starting with https://agingcoder.com/posts/2025-06-13-experiments-in-supervised-learning/ and continuing in this article https://agingcoder.com/posts/2025-06-14-experiments-in-supervised-learning-part-2/
Blogged about my experience with various AI Coding Assistants (GitHub CoPilot, Cursor, Windsurf, Junie): https://agingcoder.com/posts/2025-05-28-llms-and-coding-6-months-later/
Chris EspinosaPunk is 50, but suddenly has a new best album. And it’s by a quartet of LA high school girls. This album is pure. From the first power chord—No Obligation by The Linda Lindas https://music.apple.com/us/album/no-obligation/1752949407
