Latest / Logosofia no Dia a Dia
Can LLMs Learn Continuously Without Forgetting?
Retrieval-Augmented Generation (RAG) is standard for current AI, but it adds latency and complexity. This episode explores an alternative: micro-training LLMs to embed recent knowledge directly into their weights. We discuss the technical feasibility, the risk of catastrophic forgetting, and how LoRA adapters might solve the "goldfish memory" problem. Learn why this approach could be a game-changer for autonomous agents, despite the risks of data poisoning and the need for a "digital editor-in-chief." Episode 1700 — myweirdprompts.com/n/1700 (permanent short link: myweirdprompts.com/872884)
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.