Jeremy Morrell essay argues LLMs unlock extensible web software

Essay by Jeremy Morrell argues LLMs radically lower the cost of authoring extensions, while modern sandbox primitives cut deployment cost and provide security boundaries — enabling a 'solid, accountable core' users can safely extend. He cites Y Combinator's Pete Koomen 'Small Software' concept and Pi as an example of this LLM-native pattern.
2 sources
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Z.ai CEO Jie Tang: GLM 5.3 gains come from RL, not parameter count
- New tool adds 14 skills to Claude Code and Cursor for Markdown diagrams
- Tool turns Claude into a team of AI employees on your Mac
- GOP panics over Big Tech ties as Trump shifts on AI regulation
- Ethan Mollick: Claude's skill creator beats ChatGPT for reusable skills