Large language models

Attribution

This chapter reuses material from Learn Programming for Engineers. Find out more here and is written by Stanislaw Ostyk-Narbutt.

Programming often requires writing repetitive code and debugging nasty errors. These tasks can be time-consuming and may distract you from your original goal of solving a problem or building a feature.

Large Language Models can be especially useful in this context, as they can be trained on large amounts of code to provide intelligent code completions, suggestions, and even bug fixes. It is common practice in today’s software development landscape to use AI-powered tools to help with writing code. This concept in programming came to be known as pair programming with AI, which stems from the notion of pair programming, which is when two developers write code together, allowing them to spot each other’s mistakes and collaborate on ideas while programming. Pair programming with AI has become so powerful that even in a top-tier company like Google which only hires the best programmers, CEO Sundar Pichai made a statement that over 25% of Google’s code is now written by AI, and this number is expected to grow in the future. This shows how AI is revolutionizing the way we write code.

However, LLMs are not perfect and can sometimes produce incorrect or nonsensical outputs. It’s important to use them as a supplement to your own knowledge and skills, rather than relying on them entirely. In this chapter you’ll learn more about how to use large language models effectively.