Research
Topic

Research

Explorations into LLM reasoning, explainable AI, Apple Intelligence, and machine learning foundations.

6 posts · updated weekly
SystemsEngineeringFindingsResearchInference
Most recent
Project Glasswing: Anthropic's First Numbers
Research

May 26, 2026 · 2 min read

Project Glasswing: Anthropic's First Numbers

In one month a restricted Claude model scanned over 1,000 open-source projects and isolated more than 10,000 high or critical severity bugs.

Are LLMs Actually Thinking?
Research

Feb 05, 2025 · 2 min read

Are LLMs Actually Thinking?

Tokens, vectors, attention, and next-token prediction. What is actually happening underneath something that feels like a conversation.

Explainable AI: Opening the Black Box with SHAP and LIME
Research

Oct 22, 2024 · 4 min read

Explainable AI: Opening the Black Box with SHAP and LIME

High test accuracy is meaningless if a model exploits spurious correlations. How cooperative game theory and local linear surrogates bring mathematical interpretability to deep learning.

Logistic Regression Explained
Research

Oct 05, 2024 · 2 min read

Logistic Regression Explained

Despite the name, it is a classification algorithm. It models the probability of a binary outcome from one or more predictor variables.

Linear Regression Explained
Research

Sep 28, 2024 · 2 min read

Linear Regression Explained

A supervised algorithm that models the relationship between your features and a target, on the assumption that the relationship is a straight line.

Apple Registered genai.apple.com: Unpacking the Apple Intelligence Architecture
Research

May 25, 2024 · 3 min read

Apple Registered genai.apple.com: Unpacking the Apple Intelligence Architecture

What the registration of genai.apple.com signaled: on-device 3B foundation models, the Apple Neural Engine, and the verifiable security of Private Cloud Compute.

Sorted by most recent.