AI Model Expansion
Jeremy discusses a breakthrough in AI training by adding extended blocks to a model, allowing it to learn new skills without forgetting previous knowledge. The technique shows promise in overcoming catastrophic forgetting and achieving a better trade-off between specialized skills and general reasoning.In this clip
From this podcast
Last Week in AI
#151 - Copilot Pro, LLama.cpp, conversational diagnostic AI, secret AI diplomacy
Related Questions
How are large language models (LLMs) trained, as discussed in the episode 670: LLaMA: GPT-3 performance, 10x smaller — with Jon Krohn (@JonKrohnLearns) and the clip Llama Model Insights?
How are Large Language Models (LLMs) fine-tuned post-training in the episode Teaching Large Language Models to Reason with Reinforcement Learning with Alex Havrilla - 680 and the clip Exploration and Diversity?