Context Window Challenges
Nick discusses the limitations of current retrieval augmented generation systems, especially when dealing with extensive data like case law or personal history. Tim envisions a future where models remember everything about users, raising concerns about the implications for benchmarking and individual experiences. Both agree that while large language models hold transformative potential, they have yet to integrate seamlessly into everyday technology.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Cohere co-founder Nick Frosst on building LLM apps for business
Related Questions
Do I get it right that a Retrieval Augmented Generation (RAG) system can retrieve data in addition to its training data, as discussed in the episode with Cohere co-founder Nick Frosst on building LLM apps for business and the clip Model Evaluation Insights?
Do I get it right that a Retrieval Augmented Generation (RAG) system can retrieve data in addition to its training data as discussed in the episode with Cohere co-founder Nick Frosst on building LLM apps for business and the clip Model Evaluation Insights?