Slide 10
Slide 10 text
e.g. Unit Test Generation
● TestGen-LLM by Meta
While many, including myself, are excited about the TestGen-LLM paper and tool, in this post we have shared its
limitations. I believe that we are still in the era of AI assistants and not AI teammates who run fully automated
workflows. (https://www.qodo.ai/blog/we-created-the-first-open-source-implementation-of-metas-testgen-llm)
● ChatUnitTest
the constraint on context length imposes a limitation on the capacity of LLMs to process all relevant information and
generate a comprehensive unit test. Although recent LLMs exhibit the ability to handle longer contexts as input, it
remains imperative to provide concise and precise context to LLMs for reasons of economic cost and the
lost-in-the-middle effect (https://arxiv.org/pdf/2305.04764)
10