Development/AI policy
TDF LibreOffice Document Liberation Project Community Blogs Weblate Nextcloud Redmine Ask LibreOffice Donate
Policy on using generative AI (Large Language Models) in contributing to LibreOffice
While the use of generative AI based on Large Language Models in software development has several issues, they are allowed in LibreOffice contributions with certain restrictions.
You must be able to explain in your own words every changed line of code in a patch you created with the help of an LLM.
You must disclose the use of an LLM in the commit message, mentioning the product and version used and the steps taken. Point out the line numbers where an LLM was involved.
You must not use an LLM to generate the commit message in your patch.
You must not use an LLM to communicate with others in code review, developer chat or mailing lists.
You must not use an LLM to solve easy hacks.
You must not use an LLM to write reports related to internship projects such as Google Summer of Code or Outreachy.
If you intend to use an LLM to make lots of patches in one area, start small to avoid having to make many changes after code review feedback.
If you are using LLMs or considering to start using them, please research the topics of skill atrophy and the risks of harm to cognitive abilities related to their use.