LLM Transparency
The article discusses the use of large language models (LLMs) in a project, emphasizing the importance of human oversight. While LLMs assist in coding and writing, all content is ultimately reviewed by the author to maintain quality and intent. The author remains responsible for design decisions and the integrity of the codebase, despite the involvement of LLMs in the process.
- ▪LLMs are used as authoring and coding aids under human direction, not as fully autonomous authors.
- ▪The author reviews all content produced with LLM assistance to ensure it aligns with their voice and intent.
- ▪Python docstrings and comments in example notebooks are auto-generated by LLMs, but the source of truth remains the author's code.
Opening excerpt (first ~120 words) tap to expand
🤖 LLM Transparency This page describes how LLMs were (and continue to be) used on this project, so that readers can weigh the codebase, the documentation, and the accompanying paper with the right context in mind. We highly respect that readers expect human-written content. The majority of texts in this repository are human-typed; LLMs are used as authoring and coding aids under iterative human direction, not as fully autonomous authors. Codebase A large portion of this codebase was written with GitHub Copilot in the early stages. Nearly all subsequent coding has been carried out through vibe coding with Claude Code and Codex since they became available. All has been human-reviewed by the author before being made public.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.