When AI hallucinates reality – Fallacies of language models and the challenges of recognizing them – Part I.
Large Language Models (LLMs) generate impressive answers, but sometimes confidently assert untruths - this is called hallucination. A recent study shows that automatic detection of these errors is theoretically impossible if the models learn only from correct examples. Yet, in
AI Fatigue: When Artificial Intelligence No Longer Helps but Exhausts
The rise of AI has become unstoppable, but with it a less visible problem is also becoming increasingly urgent: AI fatigue. Why does it develop and how can it be prevented? What signs are worth paying attention to, and how
Managing AI Agents: Risk, Compliance, and Responsible Deployment (Part II.)
In the first part, we explored how the OpenAI Agents SDK simplifies the development and deployment of intelligent agents, and what key legal and data protection considerations must be considered when implementing them. Now, we are taking a deeper dive:
Managing AI Agents: Risk, Compliance, and Responsible Deployment (Part I.)
Developing AI agents has been a complex, time-consuming, and technically challenging task – but OpenAI’s new Agents SDK could change that. The new development kit allows you to build domain-specific agents that can collaborate, make decisions, and take on tasks
Knowledge Graphs and LLMs: How Can We Move from Structured Knowledge to AI-Generated Answers? – Part II.
Knowledge Graphs are therefore an advantage where information does not come from a single source, but is scattered across multiple documents, and when identifying the links between individual data point is essential to provide an accurate response. While vector search
Knowledge Graphs and LLMs: How Can We Move from Structured Knowledge to AI-Generated Answers? – Part I.
With the development of Artificial Intelligence, there is a growing need for efficient processing and use of data. Knowledge Graphs are a well-established solution for representing structured knowledge, while Large Language Models (LLMs) generate natural language responses. But do these
A potential foster care reform with the use of AI
Around the world, the foster care system is facing a crisis, with over 400,000 children in the U.S. alone being in the system on any given day. Despite billions spent annually, and an astonishing $94.4 billion allocated to the Administration
The Secret of ChatGPT: Why Does It Lag Far Behind the Agentic Systems of the (Near) Future?
In a previous post, we have already explained in broad and rather abstract terms the capabilities promised by agentic AI systems. Now we will (in a slightly lighter tone) look at the capabilities that perhaps one of the most popular
2024: Breakthroughs in AI – Innovation, Competition, and the Transformation of Society – Part II.
One of the most striking trends of 2024 was the rapid advance of multimodal Artificial Intelligence. The evolution of technology has gone far beyond text processing: the latest versions of ChatGPT, such as the 4o model and the version with
2024: Breakthroughs in AI – Innovation, Competition and the Transformation of Society – Part I.
2024 has proven to be a landmark in the world of Artificial Intelligence, with a series of exciting innovations and milestones reshaping industries, the way humans and machines work together, and setting new standards in many areas. Now, at the