Sourav Rudra writes that the GNOME Shell Extension review process is being overwhelmed by low-quality submissions generated by large language models. In response to a continued deluge of poorly coded content despite previous guidelines, developer Javad Rahmatzadeh has drafted specific technical instructions aimed at guiding these automated models toward better coding practices. This new approach seeks to minimize manual review strain by addressing common mistakes like unnecessary error handling and improper resource cleanup directly through model prompting instructions.
- Guidance advises bots to target a single GNOME Shell version rather than attempting broad compatibility via overengineering.
- New rules require personal use LLM-generated extensions to include a specific disclaimer in the code comments.
- Common errors being addressed include failing to properly disconnect signals or destroy widgets during cleanup.
- Guidance advises bots to target a single GNOME Shell version rather than attempting broad compatibility via overengineering.
- New rules require personal use LLM-generated extensions to include a specific disclaimer in the code comments.
- Common errors being addressed include failing to properly disconnect signals or destroy widgets during cleanup.
