- Published on
Why even the smartest AI models sometimes prefer to please you rather than tell the truth — and how to fight back.
5 min read
Read more →I'm Rohith, a Research Scientist at the Centre for Development of Telematics (C-DOT), and a deep learning enthusiast with a passion for peeling back the layers of multimodal machine learning systems. This blog is intended to make recent advances easier to grasp, and is an open invitation to think deeper, explore further, and stay curious about the evolving landscapes of AI.
Enjoyed what you read? I'd love to hear your thoughts—feel free drop a comment on any article. For updates on new posts, Subscribe to the newsletter and get the latest straight to your inbox 📬.
Showing 23 of 23 posts