New heise article on AI Assistants and LLMs
Michael Koppmann, senior information security consultant and Alexander Schatten, senior researcher at SBA Research, published an interesting article regarding KI Assistants and LLMs and how to check the code quality on heise online.
© Niklas Schnaubelt
© Marcel Lehner
The extent to which AI assistants and large language models (LLMs) are useful in the software development process depends on how good their output is. This sounds trivial, but it is not. Because the underlying problem is: what is code quality, how can it be measured and how do LLMs and AI assistants perform in this respect? It is also important to observe how the quality of the generated code changes over time. In order to reliably design the use of LLMs and AI in real projects, regular and ideally standardized tests are needed to assess changes in code quality.
Links
KI-Assistenten und LLMs (article)
heise online