Tag: Training Data
-
Google Adjusts Data Storage for AI Training
—
Google recently changed its privacy settings and can now store additional user data, including images, files, and audio and video recordings. This data may be used to improve and train its own AI models unless users opt out. This also includes images uploaded via Google Lens, as well as voice input and audio recordings. Voice…
-
When AI models adopt users’ assumptions
AI applications are designed to make tasks easier by adapting to individual ways of working over time. They may store preferred writing styles, recurring topics or contextual information. In theory, this should help them develop a better understanding of users and their needs. New research, however, suggests that this adaptability can also create problems. Researchers…
-
Unlocking knowledge from people: new use cases for AI
This week, we attended an event hosted by the Economic Advisory Council of Bavaria on the future of knowledge work in the age of AI. One particularly interesting perspective came from a keynote by Dr Andreas Vogel, CEO of Wisdom Bridge AI. The focus was on an area of application that is becoming increasingly relevant…
-
Factors affecting the consistency of AI systems
—
Recent reports of an alleged decline in the performance of Opus 4.6 have drawn criticism: the model is said to read less code, stop earlier and require more corrections on complex tasks. However, there is no direct evidence that Anthropic has deliberately weakened the model itself. It is more likely that changes in operating conditions…