Why human syntax breaks LLMs (and how to fix agentic coding)

Why human syntax breaks LLMs (and how to fix agentic coding)

4 pointsby aslang3 comments

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

  • Hacker News
  • I dont know but the article does not open for me
  • Interesting benchmarks. One thing I'd love to see separated out: how much of the gap is syntax vs. how much is the model just having seen far less of the "fixed" form in training. A simpler grammar with zero corpus behind it could easily perform worse in practice.
  • Very interesting. This has some overlap with my lisp + runtime approach and sema-lang.

    See https://sema-lang.com/ (which I just found today) and https://ptc-runner.dev/blog/tools-built-for-llms/

    But I love your focus on local development using smaller models.

Explore Birbla archives