AI's favorite coding language is also the most expensive
A recent study indicates that Ruby outperforms Python and TypeScript in agentic coding tasks. The author conducted tests to compare the efficiency and speed of the three languages, finding that Ruby was generally faster and more token-efficient. Despite improvements, Python struggled significantly in performance due to its complex environment setup.
- ▪Ruby was found to be the fastest and most token-efficient language for agentic coding tasks.
- ▪Python's performance lagged behind, primarily due to its complicated environment setup and multiple verification steps.
- ▪Standardizing the Python environment led to some improvements, but it still did not match the efficiency of Ruby.
Opening excerpt (first ~120 words) tap to expand
AI’s favorite coding language is also the most expensiveI ran the same agentic coding task 19 times across three languages. Ruby won on efficiency & speed. Python flunked big time.Michael CarrollMay 19, 2026ShareTrying my own rage baitAbout 3 months ago I posted a study on LinkedIn that suggested Ruby is a strong language choice for agentic coding, which got more than a few accusations of being “rage bait”.In my last post, I doubled down on the claim that AI agentic coding performs better — faster, fewer tokens — with Ruby than TypeScript and Python, the two other languages Coolhand Labs maintains packages for. Recently, I found an opportunity to quantify and test that observation. I needed to add the same, relatively straightforward, feature across all three client packages.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Hacker News (AI / LLM).
Discussion
0 commentsMore from Hacker News (AI / LLM)
