InfoWorld

Output from vibe coding tools prone to critical security flaws, study finds

The assessment, which it conducted in December 2025, compared five of the best-known vibe coding tools — Claude Code, OpenAI Codex, Cursor, Replit, and Devin — by using pre-defined prompts to build ...
InfoQ

Java Concurrency from the Trenches: Lessons Learned in the Wild

Hugo Marques explains how to navigate Java concurrency at scale, moving beyond simple frameworks to solve high-throughput IO ...
GitHub

A Python-based AI agent that replicates Cursor's coding assistant capabilities, enabling function calling, code generation, and intelligent coding assistance with Claude ...

read_file: Read file contents with flexible line range control edit_file: Make precise edits to files with clear instructions Supports complete file replacement ...
IEEE

Iterative Generation of Adversarial Example for Deep Code Models

Abstract: Deep code models are vulnerable to adversarial attacks, making it possible for semantically identical inputs to trigger different responses. Current black-box attack methods typically ...
IEEE

Computational Electromagnetics Code Validation and the Electromagnetic Code Consortium: Case studies, challenges, lessons learned, and recommendations.

Abstract: We examine validation of computational electromagnetic (CEM) codes through the lens of the Electromagnetic Code Consortium (EMCC), a group of U.S. government and associated CEM practitioners ...
GitHub

DeepCode: Open Agentic Coding

We evaluate DeepCode on the PaperBench benchmark (released by OpenAI), a rigorous testbed requiring AI agents to independently reproduce 20 ICML 2024 papers from scratch. The benchmark comprises 8,316 ...