OfficeChai

AI Models Can Understand And Improve Model Weights Through “Weight-Space Programming,” Says MIT Research

A new MIT CSAIL blog post is making the rounds in AI circles this week, and it describes something that sounds almost ...
news.lavx.hu

LLMs read and edit neural weights without gradients

Astra identifies game policies from raw weight matrices and fixes reasoning loops in Qwen3.5-0.8B by editing 0.016% of parameters, lifting MATH-500 scores from 7.9% to 48.1% without training loops.
GitHub

Expense agent

A reference LLM agent: tools, a confirmation in code, Gemini or Claude, tracing. NOVA IMS Capstone Project. - mb-cardoso/expense-agent ...
GitHub

Customer Churn Prediction Using Machine Learning

Customer Churn Prediction using Python, Exploratory Data Analysis, Random Forest and XGBoost. - Tejoshkumar/Customer-Churn-Prediction_ML ...