Quoting Jeremy Morrell

Jeremy Morrell, in a blog post titled 'Extensible Software in the age of LLMs,' argues that large language models (LLMs) create a new opportunity for extensible software on the web by lowering the cost of authoring extensions, while modern sandbox primitives reduce deployment costs and provide security boundaries, enabling apps to have a solid core that users can safely extend.

My hypothesis is that there is a new opportunity for Extensible Software on the web. LLMs radically lower the cost of authoring extensions, and modern sandbox primitives lower the deployment cost and provide good security boundaries. We can build our app as a solid, accountable core, and allow users to safely extend it in many directions by having LLMs fill in the missing pieces.We can give our users super powers. — Jeremy Morrell https://jeremymorrell.dev/blog/extensible-software-in-the-age-of-llms/ , Extensible Software in the age of LLMs Tags: sandboxing https://simonwillison.net/tags/sandboxing , llms https://simonwillison.net/tags/llms , ai https://simonwillison.net/tags/ai , generative-ai https://simonwillison.net/tags/generative-ai