Researcher Li Bojie’s “Uncompressible Knowledge Probe” uses random, black‑box API queries to gauge how much irreducible knowledge a large language model retains, allowing an indirect estimate of its effective parameter count and prompting a broader debate on model evaluation and transparency.
A new arXiv paper introduces Incompressible Knowledge Probes that estimate large language model sizes via black‑box API calls, fitting a log‑linear relation on 89 open‑source models and producing controversial parameter estimates for GPT‑5.5, Claude Opus, Gemini and others, sparking heated community debate.
This article explains the statistical foundations of AB testing, covering the Rubin causal model, SUTVA and randomization assumptions, parameter and confidence‑interval estimation, hypothesis‑testing procedures, and essential limit theorems such as the law of large numbers and the central limit theorem.
This article explains how successful mathematical modeling relies on three core components—identifying essential variables, designing an appropriate structural framework, and accurately setting parameter values—to transform real‑world problems into reliable, actionable mathematical representations.
This article explains the Expectation‑Maximization (EM) algorithm, detailing its iterative E‑step and M‑step processes, mathematical formulation, and practical Python implementation for estimating parameters of mixed linear regression models, while highlighting convergence considerations and common pitfalls.
This article explains statistical inference focusing on parameter estimation, distinguishing point estimation from interval estimation, and demonstrates how to construct confidence intervals for population means using sample data, including a practical example calculating a confidence interval for the average Sharpe ratio of equity funds.
This article explains how to identify, order‑select, estimate parameters, validate, and forecast ARMA time‑series models, covering the Akaike Information Criterion, various estimation techniques, and diagnostic tests such as the Ljung‑Box test, with practical Python implementation guidance.
This article explains the method of moments for estimating population parameters, outlines its step‑by‑step derivation, and demonstrates a Python implementation that estimates a basketball player's shooting odds from binary outcome data using.
This article explains statistical inference focusing on parameter estimation, distinguishing point and interval estimates, describing how confidence levels relate to significance levels, and illustrating the calculation of confidence intervals for population means with a practical example using Sharpe ratios from a sample of 100 observations.
This article explains the assumptions, equations, and parameter‑estimation methods of a two‑compartment pharmacokinetic model for describing drug distribution, transfer between central and peripheral spaces, and elimination, and compares common dosing routes such as rapid IV bolus, constant‑rate infusion, and oral or intramuscular administration.
