Tag
A tweet showcases a visualization of 8 LLMs' reasoning traces on a probability question, highlighting moments of self-correction and pivoting.
A visualization that shows how 8 different LLMs reason through a tricky probability question, with branches representing moments of self-correction like 'But, wait...'.
Recommend an interactive visualization website called Seeing Theory to help users intuitively understand core concepts of probability and statistics, covering basic probability, distributions, inference, regression, etc., suitable for beginners and those reviewing.
Nathan Lambert shares a video lecture covering prerequisites for his book, including language model basics, probabilities, and training pipelines, using GLM 5.2.
Mathematicians have extended the classic 1992 proof about card shuffling to less precise shuffles, showing that a 'cutoff phenomenon' still occurs even with uneven deck splits.
This paper argues that probability theory is a historically evolving form of rationality, tracing its development from combinatorial games to Bayesian inference and contrasting it with fuzzy logic and deep learning.
KL Zero is an interactive browser game where players draw a probability distribution to match a target KL divergence value, helping users intuitively understand the concept of KL divergence in machine learning.
A tweet shares a lecture at MIT by David Shirokoff covering the fundamentals of Markov Chains, including transition probabilities, Markov matrices, eigenvalues, and long-term steady state.
Jane Street offers $750k/year for quants who can apply Stochastic Processes and Markov Chains in trading, and a free MIT lecture covers similar material.
An educational essay explaining the Birthday Paradox math and its application to hash collisions in cryptography, covering probability calculations for matching birthdays and the historical context of Richard von Mises' contributions.
The article presents an elegant geometric proof for Buffon's Needle problem by extending the concept to curved 'noodles' and using a circle to determine the probability constant, avoiding complex integrals.