What's the best programming language for coding agents?
- ID
- 13160
- Status
- summarized
- Published
- 11 Aug 2026, 12:28 AM
- Fetched
- 12 Aug 2026, 11:38 PM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- http://danluu.com/pl-tokens/
- Source URL
- https://hnrss.org/best
Summary
- Score
- 7.5
- Created
- 12 Aug 2026, 11:40 PM
- Tags
- Audience
- developersvibe_codersai_ml_learners
What happened
Dan Luu critiques a widely-cited claim that dynamic/concise languages like Clojure or J are 2-3x more token-efficient for LLM coding agents than static languages like Rust or Go. He argues the benchmarks rely on trivial Rosetta Code problems (70-109 token solutions) where performance doesn't generalize, and notes methodological flaws in supporting comparisons, including a symlink bug that corrupted test results.
Why it matters
Don't choose your stack based on token-efficiency benchmarks from toy problems; if you're deciding between Python and Rust for an AI-assisted codebase, token cost on trivial tasks is not evidence of real-world agent performance. If you care about token efficiency, run your own eval on problems representative of your actual workload before committing.
Discussion angle
How much should token efficiency actually factor into language choice for AI-assisted development, and what would a credible benchmark for this look like vs. the Rosetta Code-style tests being cited today?