The original software geek. Author of 5 books and some of Clean Code. Bringing delight to software development.
Colorado Springs, United State
Joined July 2008
- Tweets12.7K
- Following648
- Followers2.4K
- Likes2.6K
Changing behavior with AADV (AI Assisted Development with Verification) new post on Substack!
jjlangr.substack.com/p/chang…
Adding new behaviors means regenerating entire modules. How do you begin to accomplish that in a well-designed, multi-module solution?
Examples: The lingua franca of AADV?
New AI Code Correct substack post!
When doing AI-assisted development with CAX, examples are the basis for compiling intent into code and tests, like a compiler produces executable artifacts.
open.substack.com/pub/jjlang…
"Behavioral drift in AADV"
LLMs hallucinate intent, too, during code generation. Why it's a problem and some thoughts on addressing it.
open.substack.com/pub/jjlang…
Many of the skills needed to succeed at AI-assisted development (with verification!) aren't terribly daunting. Learning how to supply examples to the LLM is at the core of AADV; this AI Code Correct post provides an introduction.
jjlangr.substack.com/p/aadv-…
Not "all vibe coding is bad," but defining a dev process in a tweet is irresponsible. We know how it will mostly turn out
AI Code Correct post: "Squelching bad vibe coding," in which I review my approach to AI-assisted development.
jjlangr.substack.com/p/squel…
AI Code Correct: Avoid bad vibe coding!
Latest post: A (free) follow-up to the CAX-driving of a cyclomatic complexity module.
When CAXing a cyclomatic complexity module, why did the LLM generate a non-compliant cyclomatic solution, failing two tests?
jjlangr.substack.com/p/a-del…
Jeff Langr retweeted
Spring Sale Week Two
Text, Tools, and Testing
40% Off – This Week Only!
Code: 2025testing at checkout
Titles on sale this week -
AI Code Correct: "CAXing a cyclomatic complexity model."
jjlangr.substack.com/p/caxin…
The LLM generates a solution that fails errant examples.
Fixing them gets me to 100% compliance.
Next up: Thoughts on why this occurred.
Week two of the Pragmatic Bookshelf's Spring Sale starts Wednesday April 16! Pick up a copy of Pragmatic Unit Testing in Java (3e) at a 40% discount!
lnkd.in/gEDvsfsg
Do well-designed LLM solutions comply more?
open.substack.com/pub/jjlang…
(Proposed research for LLM code generation via AADV/CAX. A true teaser--no answer yet. Help shape the research!)
"Prompt, Pray, Repeat"--latest AI Code Correct post , in which I make a hypothesis that does not hold true. The LLM does respond really well to a prompt including some specifics about the solution's design, though.
lnkd.in/gFyvXWPz
"Prompt, Pray, Repeat"--my latest AI Code Correct Substack post , in which I make a hypothesis that does not hold true. The LLM does respond really well to a prompt including some specifics about the solution's design, though.
lnkd.in/gFyvXWPz
Your LLM-generated code *will* inevitably demonstrate a compliance gap. At least you'll have tests that fail, if you're practicing CAX. What then, though?
In this post: a simple example gone wrong, and a thankfully near-effortless resolution.
jjlangr.substack.com/p/cax-f…
Looking for a new exercise for interviewing, a practice problem to learn a new language, or a first intro to TDD? The name normalizer kata:
github.com/jlangr/name-norma…
Solutions in many languages, Python conspicuously missing. I'd love a good contribution.
we must start breaking the loop: Help feed the AI models with better code, via AAD
jjlangr.substack.com/p/ai-as…
Jeff Langr retweeted
Great work @jlangr! We're honored to inform you that "Modern C++ Programming with Test-Driven Development" made it to BookAuthority's list of best Software Testing books of all time! bookauthority.org/books/best…