There's a truth that traditional ontology communities are reluctant to face: Large language models already contain world models. They're not formally axiomatized. They're not neat. They're not hand-built by committees. But they work.
LLMs tell us something about human nature, contra Chomsky. We’re not sure yet what they tell us, but there’s more going on here than big tech’s power play.
Despite conventional wisdom, RAG doesn’t address LLM’s biggest problem, i.e., hallucinations. You fix hallucinations with safe system design and I’ll tell you here what it cost us.
Get the latest on knowledge graphs, LLM, and Stardog
No spam. Unsubscribe at any time.
