Summary
We thought and learned about the limitations of LLMs in this chapter, including the lack of understanding, lack of context, high computational requirements, dependency on their training data, and security risks. We’ve also touched on some metrics for judging LLM performance.
We tried to overcome these limitations and looked at a few promising alleys for how to create greater LLMs.
This chapter also covered IP concerns, how LLMs need to be explainable, and where to learn more about these issues.
In the next chapter, we will learn about collaboration and knowledge sharing in LLM-powered coding because this is how you make real changes to the world, help people, and get your name known more.
