Viewing profile — joshua_s_penman

I've built a new method for steering LLMs called Semantic Overlays, small trained adapters on a frozen model which change how it perceives a piece of its context. The most readily …

> interesting, so you think the issue with the above approach is the graph structure being too rigid / lossy (in terms of losing semantics)? Yeah, exactly. >And embeddings are also…

this is fundamentally organized by popularity, though

The thing is — for very long documents, it's actually pretty hard for humans to find things, even with a hierarchical structure. This is why we made indexes — the original indexes!…