Tech Finally, no more time-consuming research - What is deep research? Who hasn't been there. You have to research something for
Tutorial From zero-shot prompting to RAG - Part 4: Meta prompting In the fourth part of our series, we look at meta-prompting. While
News Google A2A protocol: Agents can now do teamwork! AI agents have established themselves as valuable resources that help companies to
Tech Agentic vs. generative AI - what's the difference? Two terms that are frequently used in the context of AI are
Tutorial Von Zero-Shot-Prompten bis RAG – Teil 3: Chain-of-Thought Prompting Few-Shot Prompting is an effective and flexible method of preparing language models for new tasks - without any additional training.
News Google talks to dolphins: Google translator for animals Google has taken a remarkable step towards understanding communication with dolphins. The
Tech OpenAI presents GPT-4.1: A breakthrough in artificial intelligence Recently, OpenAI took a significant step forward in the world of artificial
Tutorial From zero-shot prompting to RAG - Part 2: Few-shot prompting Few-Shot Prompting is an effective and flexible method of preparing language models for new tasks - without any additional training.
News Sam Altman announces first new Open Weights model since GPT-2 With the announcement of the publication of an Open Weight Language Model, OpenAI is taking a decisive step towards openness and cooperation.
Tech Revolutionary lingua franca for AI agents: What is MCP? MCP provides a standardized interface to standardize the use of tools and thus significantly increase the efficiency and functionality of AI applications.
Tutorial New series: from zero-shot prompts to RAG - How YOU can make better use of LLMs Prompting depends on good and clear wording and an understanding of natural language. Nevertheless, certain techniques and methods can significantly improve the result of a prompt.
Tech Mind-reading AIs - Anthropic manages to gain insights into the "black box" for the first time. With the help of special analysis tools, a research team was able to identify neuronal activation patterns and concepts within the model that were previously only speculated.