A Practical Approach to Using LLMs: Peculiarities and Pitfalls
summary
Practical guidance on using large language models (LLMs) in real systems, focusing on concrete challenges like hallucinations, performance bottlenecks, high processing costs, and integration difficulties. Discusses engineering approaches to mitigate these issues when deploying LLMs in production for text generation tasks.
AI-written summary · about
chapters (5)
- 0:00Introduction
- 10:14LLM usage economics
- 22:54Case 1: Sentiment parser
- 31:58Case 2: Book recommendation chatbot
- 44:38Q&A
related talks
39mLLMs and Hallucinations: Understand, Measure, Control
46mUnder the Hood of LLMs — all those questions you never dared ask about them
18mBeyond the Chatbot: The Real Impact of LLMs on Observability
33mDesigning LLM Applications for Massive Datasets
51mTowards a Pragmatic Understanding of Large Language Models
33mOpening Keynote: LLMs, between fantasy and reality - the poin...
29mWhat Is It Like to Be an LLM?
45mLarge language models are not a paradigm shift