Which programming languages are most token-efficient? - Martin Alderson
martinalderson.com · 816 words · saved by 1 readers
Comparing token efficiency across 19 popular programming languages using RosettaCode data - from Clojure to C, there's a 2.6x difference.
I've been trying to think through what happens to programming languages and tooling if humans are increasingly no longer writing it. I wrote about how good agents are at porting code recently , and it got me thinking a bit more about what constraints LLMs have vs humans. One of the biggest constraints LLMs have is on context length. This is a difficult problem to solve, as memory usage rises significantly with longer context window in current transformer architectures. And with the current memory shortages, I don't think the world is drowning in memory right now. As such, for software developm
saved by
related reading
- LLM Inference Performance Engineering: Best Practices | Databricks Blogdatabricks.com
- Lean Software Scaling Laws · Gwern.netgwern.net
- Shipping at Inference-Speed | Peter Steinbergersteipete.me
- [2604.22750] How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasksarxiv.org
- Scaling long-running autonomous coding · Cursorcursor.com
- Here’s how I use LLMs to help me write codesimonwillison.net
- claude code is not making your product betterethanding.substack.com
- Malleable software in the age of LLMsgeoffreylitt.com
- Benchmarking Coding Agents on Databricks’ Multi-Million Line Codebasedatabricks.com
- LLMs can invent their own compression - Rajan Agarwalrajan.sh
- [2203.07814] Competition-Level Code Generation with AlphaCodearxiv.org
- The Bitter Lesson is coming for Tokenization – ⛰️ lucalplucalp.dev