I use plenty of libraries in my work that aren't in the training data, so I tell the coding agent to read the library source code when it needs to understand them
@simonw
-
Automating Code Generation Over Manual Programming
By
–
I'd rather that than type hundreds of lines of code by hand
-
Automated Testing and TDD Best Practices for AI Development
By
–
Step one is to have good automated tests – then approach every p by researching, planning, implementing with red/green TDD, then validating with both human-manual and coding-agent-manual testing
-
Using Coding Agents for Unambiguous Programming Language Specification
By
–
"English (nor any other natural language) is not a safe way to specify anything that needs well-defined, certain, reliable outcomes." – right, that's why I use coding agents to accelerate the process of building code in unambiguous programming languages which I then review
-
PyCon US 2026 Launches New AI and Security Tracks
By
–
Join us at PyCon US 2026 in Long Beach—we have new AI and security tracks this year
-
Claude Code grep capability transforms codebase context limitations
By
–
For me it was when Claude Code got good at grep, since then it didn't matter if the whole codebase fitted in the context or not
-
Agent-Driven Projects: Nervousness About New AI Implementations
By
–
Yeah I know what you mean, I'm a lot more nervous about some of my new mostly-agent-driven projects than I am about agent-driven changes to my older ones
-
LLMs and Coding Agents Excel Beyond Greenfield Development
By
–
Is there still a widespread belief that LLMs and coding agents are good for greenfield development but don't help for maintaining large existing codebases? I don't think that idea holds up any more