As the capabilities of AI continue to grow, it is becoming increasingly difficult for humans to supervise them. In this article, we discuss this pressing issue through the lens of a recent paper presented at ICLR 2025 by a group from Anthropic: Language Models Learn to Mislead Humans via RLHF. This paper investigates an intriguing […]
Deceptive and Lazy AIs: When Language Models Learn to Mislead Read Post »
In the field of Natural Language Processing (NLP), a central theme has always been “how to make computers understand the meaning of words.” One fundamental technique for this is “Word Embedding.” This technique converts words into numerical vectors (lists of numbers), with methods like Word2Vec and GloVe being well-known. Using these vectors allows for calculations
Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem Read Post »
“Recommended for You” YouTube, Amazon, Netflix, X, news sites… We are surrounded by services displaying recommendations. While convenient, have you ever felt, “I keep getting recommended the same kinds of things,” or “I wish I could get recommendations from a different perspective”? Or perhaps wondered, “Are these recommendations biased?” The truth is, these “recommendations” (recommender
Hack Your Feed: Take Control of Your Recommendations Read Post »
When I first began learning about machine learning, I struggled with the notion that lowering the loss on the training data does not necessarily guarantee performance on the test data, since training data and test data are different. In this article, I will carefully explain why the performance on test data is theoretically guaranteed, aiming
A Gentle Introduction to Machine Learning Theory Read Post »
I came across an intriguing post while browsing X during New Year’s holidays. Historically, humanity has pursued the idea that truth is inherently simple, exemplified by equations like \(E = mc^2\) or \(F = ma\). However, the idea presented was that such truths may represent only a small subset of the entire truth, suggesting the
The Hidden Information AI Understands but Humans Miss Read Post »
It is well known that eigenvalues of a real symmetric matrix are real values, and eigenvectors of a real symmetric matrix form an orthonormal basis. This theorem plays important roles in many fields. For example, the principal component analysis relies on this theorem. Although every textbook on linear algebra contains a proof of this theorem,
