Large Language Models are Terrible at Programming

Table of Contents Introduction Abstractions, maintenance, and tech debt The garden and the forest Conclusion Introduction Large language models (llms) were originally created by programmers and computer science or computer science-adjacent researchers. It is therefore not strange that one of the first use-cases that they were employed in, and in which they have been given an overrepresented amount of attention, is the automation of writing code — the text that describes a program. And yet, despite rapid increases in llms’ capabilities when it comes to writing code, the actual quality of the code they produce is still very low. Why is this? The debate about the usefulness of large language models, and agents in particular, is in practice over. The field of software development has changed radically in the four years since the release of gpt 3.5, and is almost unrecognizable. There are still hold outs, and the degree to which agents are used differs drastically from person to person,…

Commenting on Bubbles has been removed. Why? If you want to talk about this post, write to the author, use the comments on their blog if it has them, or reply with a "RE:" post on your own blog. Suggestions? feedback@bubbles.town