Deep Learning
5 pieces on Deep Learning.
News & Analysis
RLT Runs 96 Blocks Per Token With Recurrent State, No Resets
Princeton's Recurrent Looped Transformer carries full decoder state across every token with 96 logical blocks and no prompt-response boundary reset.
Read more →
Why σ(x) = 1/(1+e⁻ˣ): The Derivation Behind Sigmoid
Most practitioners memorise sigmoid but skip the derivation. Here's why e appears, how the (0,1) bound is constructed, and what it means for backpropagation.
Read more →
Why Transformers Look the Way They Do: Deriving Q, K, and V
A step-by-step reconstruction of the Transformer shows that queries, keys, values, and W₀ are near-inevitable answers to concrete engineering problems.
Read more →
The Architecture of Intelligence: AI vs. Machine Learning vs. Deep Learning
They are often used interchangeably in boardrooms, but these three terms represent distinct, evolutionary steps in computer science.
Read more →
Solving AI Hallucinations: Fact-checking Pipelines Explained
How modern architectures use strict fact-checking pipelines and grounding mechanics to mathematically force LLMs to tell the truth.
Read more →