No matter how great a note-taking app is, my emails are going to live outside of it. No matter how seamless the experience in my contacts app, my text conversations are going to live outside of it. We should acknowledge this fundamental limitation of the “note-taking app” approach to building tools for thought, and shift our focus away from building such siloed apps to designing something that lives on top of these smaller alcoves of personal knowledge to help us organize it regardless of its provenance.
Linus Lee. The Web Browser as a Tool of Thought.
Agreed.
I love using Obsidian for note-taking and academic writing, but even though all my notes are in Markdown and therefore accessible to almost all other apps, they’re still separate in a meaningful sense. I can’t connect a paragraph of text in a markdown file with a sentence in an email I received, or to a PDF, or to slide in a PowerPoint deck.
No matter how feature-rich or user-friendly a note-taking app might be, it inevitably faces a critical limitation – it can’t encompass the entirety of our digital lives. This fragmentation isn’t just an inconvenience; it’s a barrier to building a comprehensive and connected personal knowledge management system.
The challenge we face is not just about storing information, but about creating meaningful connections across different types of data and various platforms. As I reflect on my own experience, I find that even with powerful tools like Obsidian – which I use extensively for note-taking and academic writing – there are still limitations. Despite the universal accessibility of Markdown files, I can’t easily link a paragraph in my notes to a sentence in an email, a section of a PDF, or a slide in a PowerPoint presentation.
- The browser as a hub (this is the approach described by Linus in the post above. Given that a significant portion of our digital interactions occur through web browsers, they could potentially serve as a unifying platform. However, this approach still falls short for applications and data that live outside the browser environment.
- Operating system integration: Another possibility is building this functionality directly into the operating system or as a layer just above it. This approach is reminiscent of the semantic desktop project I described back in 2008, which aimed to bring semantic web technologies to the desktop environment.
- Small language models: Perhaps the most promising avenue is the development of small, efficient language models that can run locally on our devices. These models, like Microsoft’s Phi-3, could potentially access and understand all the information on our computers and digital lives, creating connections and insights across different platforms and file formats.
Linus is right when he says that no “single app can be my second brain”; instead, it’s going to be something that sits above all apps. The future of personal knowledge management isn’t about finding the perfect note-taking app – it’s about creating a seamless, intelligent layer that turns our entire digital life into a cohesive, interconnected knowledge ecosystem.