1
LLM Voice
The uncanny valley of LLMs' prose
Martin Fowler
A website on building software effectively
- Popular posts
- 84
- Total points
- 17,806
- HN comments
- 10,168
- Rank
- #33 personal
Visit martinfowler.com → On Hacker News Jun 2009 – Oct 2026
Software Engineering 66Career & Management 20Tech Industry & Business 15AI & Machine Learning 13Society, Policy & Culture 10Systems & Performance 8
2
An example of LLM prompting for programming
Generated knowledge and chain of thought prompting of an LLM can generate useful code.
3
Some thoughts on LLMs and software development
a short post
4
The role of developer skills in agentic coding
Notes from my colleagues on AI-assisted software delivery
5
I Don't Like LLMs
a short post
6
The Future of AI Software Development
Detailed report on the Thoughtworks AI retreat, should we write a manifesto for AI-enabled development, is spec-driven development the return of waterfall, LLMs perform better in healthy codebases
7
Building your own CLI coding agent with Pydantic-AI
How to build a CLI coding agent
8
Building reliable agentic AI systems
AI helping pharmaceutical researchers query decades of information buried in PDF reports
9
Building Boba AI: Lessons learnt in building an LLM-powered application
A series of patterns for building an AI co-pilot application.
10
The Learning Loop and LLMs
How continuous learning shapes effective software development with LLMs
11
Understanding Spec-Driven-Development: Kiro, Spec-Kit, and Tessl
Notes from my colleagues on AI-assisted software delivery
12
DSLs Enable Reliable Use of LLMs
Why Domain-Specific Languages and good abstractions make LLM code generation reliable and reviewable.
13
Why are good developers so wary of agentic development?
Good developers’ caution about agentic development comes from knowing that built isn’t the same as working in production.