GitHub

SPADE: Sparsity Guided Debugging for Deep Neural Networks

This repository contains the code for the paper "SPADE: Sparsity Guided Debugging for Deep Neural Networks". In this paper we improved interpretability methods by first pruning the model on the sample ...
IEEE

Balancing Security and Correctness in Code Generation: An Empirical Study on Commercial Large Language Models

Abstract: Large language models (LLMs) continue to be adopted for a multitude of previously manual tasks, with code generation as a prominent use. Multiple commercial models have seen wide adoption ...
Geeky Gadgets

ChatGPT 5.3 Codex Moves Ahead on Code, While Claude’s 4.6 AI Banks on Reliability

What if the future of coding wasn’t just faster, but smarter, safer, and more collaborative than ever before? In this walkthrough, Better Stack shows how the latest advancements in AI coding models, ...
IEEE

WIP: Code Insight: Combining Code Reading and Debugging Practices for Active Learning in Entry-Level Computer Science Courses

Abstract: This work-in-progress innovative practice paper describes an active learning in-class activity to be used in introductory programming courses. In the software development industry, critical ...
Fast Company

Anthropic’s new Claude Opus 4.6 aims to think through bigger code bases

Anthropic is out with a new model called Claude Opus 4.6, an upgrade to its top-of-the-line Opus 4.5 model that launched in November. The new release could add new capabilities to Anthropic’s Claude ...