What's the best programming language for coding agents?

I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.

An analysis and critique of claims that dynamic programming languages are more token-efficient than static languages for LLM coding agents, examining methodological flaws in the studies behind those claims. The piece argues that conclusions drawn from trivial benchmark problems don't generalize to real-world coding tasks.

danluu.com →

Connections

Related to

How Frontier Teams Are Reinventing AI-Native Development Frontier AI-native development teams face exactly the language-choice question the new item addresses; the methodological critique is directly relevant to engineering decisions discussed in how frontier teams reinvent AI-native development.
Strands AI Functions: Python Library for Verified Agent Workflows Strands AI Functions is a Python library for agent workflows — Python being a dynamic language makes it a direct subject of the token-efficiency debate the new item critiques, grounding the abstract analysis in a concrete tooling example.
Formal Methods at Jane Street: Agentic Coding Changes the Calculus Both examine language choice for AI coding agents — the new item critiques claims about dynamic vs static languages, while Jane Street's piece specifically argues formal/static methods become more valuable in agentic coding contexts, offering a counterpoint perspective.
TerminalWidget for Mac, iPhone, and iPad Weaker connection — keeping stronger ones instead.

Supports

Building an Advanced Agentic Harness Building an advanced agentic harness requires understanding what language properties actually matter for agent reliability; the new item's methodological critique helps practitioners make more evidence-based language choices for harness construction.
8 Myths of Software Development with AI Both are myth-busting analyses of AI development claims — the new item critiques token-efficiency studies for dynamic languages, while '8 Myths of Software Development with AI' similarly challenges popular but poorly-evidenced beliefs about AI coding.

Challenges

TerminalWidget for Mac, iPhone, and iPad Token efficiency claims for dynamic languages are directly relevant to LLM-driven terminal/CLI tools; the new item's critique challenges assumptions that may underpin tooling design decisions like those behind TerminalWidget.

Supported by

Bullet: Fast Coding Agent Bullet's design choices around task routing and parallel tool calls provide concrete evidence for the discussion of what programming language and architectural decisions best serve coding agents

Type:	link
First published:	Tuesday, 11 August 2026 at 01:09 UTC
Location:	https://danluu.com/pl-tokens/
URL:	https://mattwood.fyi/i/41b43915