IEEE

LLM-based Interactive Code Generation: Empirical Evaluation

Abstract: Recently, large language models (LLMs), those pretrained on code, have demonstrated strong capabilities in generating programs from informal natural language intent. However, LLM -generated ...
InfoWorld

What I learned using Claude Sonnet to migrate Python to Rust

Using an AI coding assistant to migrate an application from one programming language to another wasn’t as easy as it looked.

Rust: The Unlikely Engine Of The Vibe Coding Era

In 2025, something unexpected happened. The programming language most notorious for its difficulty became the go-to choice ...
IEEE

DemoCraft: Using In-Context Learning to Improve Code Generation in Large Language Models

Abstract: Producing executable code from natural-language directives via Large Language Models (LLMs) involves obstacles like semantic uncertainty and the requirement for task-focused context ...
GitHub

Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation

[2025-06-01] Many thanks to @aherzinger for implementing and refactoring the Generator and RAG models. [2025-05-30] Huge thanks to @baraayusry for implementing the Online Retriever using CrawAI and ...
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 ...
New York Post

Gen Z — the first generation officially dubbed dumber than the last

Gen Z, this will smart. The generation born between 1997 and 2010 is the very first generation who did worse in school than the generation before them, according to a top neuroscientist. And ...