As context windows get larger and larger, one question that keeps coming up is whether retrieval augmented generation or RAG is becoming obsolete.
Why listen
It goes beyond the title with direct discussion of know, like, think, including: If models can ingest millions of tokens of context and reason over enormous collections of documents, why bother with retrieval at all?.
Key takeaways
01As context windows get larger and larger, one question that keeps coming up is whether retrieval augmented generation or RAG is becoming obsolete
02If models can ingest millions of tokens of context and reason over enormous collections of documents, why bother with retrieval at all?
03I recently sat down with Alex Bocut, head of engineering at Sphere, which builds AI systems for sales tax automation and compliance
Best for
listeners looking for a practical AI episode debrief