I’m extremely curious about the design process of the knowledge base. Just learning about ClaudePlaysPokemon today and I’m a bit surprised at how naive the store is. There’s a reasonably large amount of research into artificial neural network memory and I’ve suspected for a few years that improvements in knowledge scaffolding is promising for really overcoming hallucinations and now reasoning deficiencies. It’s to the extent that I’ve supported projects and experiments at work to mature knowledge bases and knowledge graphs in anticipation of marrying them to an LLM (non-agentic but potentially agentic in the future).
I wonder if any of the literature from sites like this could help in designing better reasoning scaffolding, one would think rationalism is precisely about systematizing how and why we retain awareness of the world.
I’m extremely curious about the design process of the knowledge base. Just learning about ClaudePlaysPokemon today and I’m a bit surprised at how naive the store is. There’s a reasonably large amount of research into artificial neural network memory and I’ve suspected for a few years that improvements in knowledge scaffolding is promising for really overcoming hallucinations and now reasoning deficiencies. It’s to the extent that I’ve supported projects and experiments at work to mature knowledge bases and knowledge graphs in anticipation of marrying them to an LLM (non-agentic but potentially agentic in the future).
I wonder if any of the literature from sites like this could help in designing better reasoning scaffolding, one would think rationalism is precisely about systematizing how and why we retain awareness of the world.