... reasoning, or tricky knowledge. But for AI, the definition might be different. Some things that feel easy for us can be surprisingly hard for models, while things that seem tough for us (like scanning huge datasets quickly) might be trivial for them. So, I m curious how do you think about this? What do you consider a complex problem when working with LLMs? Comment from Jason Gelsomino(@jason_gelsomino): @ahmad63  That's a perfect analogy for comparing models... Comment ... ... marathon runner both great, just built for completely different terrains. Comment from Ahmad(@ahmad63): @jason_gelsomino   @marcello_cultrera1  Beautifully said semantic scaffolding is exactly it. You can feel when a model has structure beneath the surface versus

... accidentally deleted a really critical note and there was no recourse), but generally, I like everything else. I've heard lots of people talk about @Obsidian , but I've been reluctant to explore it because it seems non-trivial to set up syncing, and I'm dreading making the transition (I never transitioned my Evernote notes due to lots of rich media - audio notes... so my augmented memory is kinda split between pre-2016 and post-2016). So... should ...