Welcome to Tensors & Quarks
Exploring the cosmos of Physics & the depths of Machine Learning.
Latest Posts
-
Can Quantum Mechanics Describe Reality? A Tale of Two Papers
In the spring of 1935, two scientific giants—Albert Einstein and Niels Bohr—stood on opposite sides of a profound question: Is quantum mechanics a complete description of reality? That question became the title of two iconic papers, published in the same year, each offering diametrically opposed answers. This wasn’t just a scientific disagreement; it was a philosophical clash that would shape the direction of physics for decades.
Read more → -
From Circuits to Cognition: Following the Thoughts of Claude 3.5
Decoding Anthropic’s Next Step in Understanding Language Models
In my previous post, we explored “On the Biology of a Large Language Model”, Anthropic’s groundbreaking research that mapped the internal circuits of Claude 3.5 Haiku using attribution graphs. These graphs offered a glimpse into the hidden architecture of reasoning — showing how Claude decomposes questions, plans poems, reasons across languages, and even hallucinates.
Read more → -
From Black Box to Blueprint: Tracing the Logic of Claude 3.5
Exploring the Hidden Anatomy of a Language Model
In the age of large language models, capability often outpaces comprehension. Models like Claude 3.5 can write poetry, solve logic puzzles, and navigate multilingual queries — but we still don’t fully understand how. Beneath their fluent outputs lies a vast architecture of layers, weights, and attention heads that, until recently, remained largely inscrutable.
Read more → -
The Deepening Layers of Inception: A Journey Through CNN Time
The story of the Inception architecture is one of ingenuity, iteration, and elegance in the field of deep learning. At a time when researchers were obsessed with increasing the depth and complexity of convolutional neural networks (CNNs) to improve accuracy on large-scale visual tasks, Google’s research team asked a different question: How can we go deeper without paying the full computational price? The answer was Inception—a family of architectures that offered a bold new design paradigm, prioritizing both computational efficiency and representational power. From Inception v1 (GoogLeNet) to Inception-ResNet v2, each version brought transformative ideas that would ripple throughout the deep learning community. This post unpacks the entire journey, layer by layer, innovation by innovation.
Read more → -
How ImageNet Taught Machines to See
The Vision Behind the Dataset
In the early 2000s, artificial intelligence was still stumbling in the dark when it came to understanding images. Researchers had built systems that could play chess or perform basic language tasks, but when it came to something a toddler could do—like identifying a cat in a photo—machines struggled. There was a glaring gap between the potential of machine learning and its real-world applications in vision.
Read more →