Rafael Tappe Maestro

The itemis blog

Rafael Tappe Maestro is a research scientist at itemis AG in Germany. He pursues a master’s degree in artificial intelligence at the University of Groningen. His AI research interests are on energy constraints, neural architecture search and local learning rules. Rafael enjoys reading Phoronix Linux news and starring projects on GitHub.

Data Science, Machine Learning, A.I.

natlagram: Creating Diagrams From Text With the Help of GPT and Kroki

Natlagram is a tool that allows users to generate diagrams from their natural language descriptions. This application is built around OpenAI's GPT and the Kroki diagram tool, making it easy for users to describe structures and processes from any domain to receive ...

by Rafael Tappe Maestro

21 min. reading time
Machine Learning, A.I.

The Rise of Large Language Models ~ Part 2: Model Attacks, Exploits, and Vulnerabilities

Large Language Models (LLMs) like ChatGPT have the potential to revolutionize the way we access information and build software. However, the integration of these models with software also poses some risks that need to be addressed. In this blog post, we will ...

by Rafael Tappe Maestro

5 min. reading time
Machine Learning, A.I.

The Rise of Large Language Models ~ Part 1: Impact on Power, Privacy, and Security

It's been two months since OpenAI released its latest large language model, ChatGPT, and it's already making waves in the tech world. ChatGPT presents itself as a tool for translation, information retrieval, poetry, essays, and program code, but it has the ...

by Rafael Tappe Maestro

3 min. reading time

natlagram: Creating Diagrams From Text With the Help of GPT and Kroki

The Rise of Large Language Models ~ Part 2: Model Attacks, Exploits, and Vulnerabilities

The Rise of Large Language Models ~ Part 1: Impact on Power, Privacy, and Security