LLM What LLMs Can and Cannot Do Will the capabilities of LLMs increase or plateau? Are current AI systems already good enough to cause significant transformation? Join me on a quick exploration of the possibilities and limitations of today's predominant AI paradigm.
NLP gerenbench - A Small Proprietary Benchmark for German RAG RAG connects proprietary data to LLMs. This article presents results of "gerenbench", a small proprietary benchmark that uses German encyclopedia articles to estimate the accuracy of LLMs on RAG tasks.
NLP LLM Update I don’t use Large Language Models (LLMs) to write articles on my blog. I use them heavily behind the scenes, though.
