91 stories tagged Coding
ETH Zurich tested 100 developers in a controlled 'vibe coding' environment. The study found that developers with strong computer science foundations significantly outperformed others, challenging the idea that vibe coding can replace traditional training.
Checkly used AI agents to rewrite a critical Node.js service processing 92 million messages daily into Go, achieving significant performance and reliability improvements. The project demonstrates that AI can handle large-scale codebase refactoring.
Security researchers at Intezer found 227 instances where AI coding assistants Claude, Codex, and Hermes generated install commands pointing to code no one owns. The discovery reveals a systemic supply-chain risk in AI-assisted development.
Researchers propose a two-layer detector that catches 'slopsquatting' attacks, where AI coding assistants hallucinate non-existent Python package names that adversaries can pre-register on PyPI to compromise the software supply chain.
OpenAI released GPT-5.6 in Kiro, a cost-effective AI model optimized for software development tasks like planning, building, reviewing, and testing code, with improved price-performance.
Replit has introduced Free Mode, powered by GPT-5.6 Luna, allowing anyone to create software without worrying about token costs. This move democratizes software development by removing financial barriers.
ProofRun is an open-source tool that generates local verification receipts for code produced by AI coding agents, providing a verifiable record of execution and output to ensure reliability.
A first-of-its-kind analysis of 761 million LLM calls from GitHub Copilot traces reveals that AI coding agents produce sparse, autonomous workloads distinct from chatbots, with major implications for AI system design and infrastructure.
Researchers introduced TraceCoder, an AI coding tool that records every step of code generation. It makes AI-generated code fully transparent and auditable, addressing key limitations of current systems.
A developer open-sourced jcode, a coding agent harness that boots 245 times faster than Claude Code, rendering its first frame in 14 milliseconds and using only 27.8 MB of RAM per active session.
A new OpenAI field report details how scientists use AI coding agents to modernize scientific computing, accelerating software development and discovery in genomics and beyond.
OpenAI introduced an AI-powered keypad that helps coders write and debug code faster. While exciting for developers, it might be confusing for non-technical users.
Cognikernel is a new open-source tool that gives AI coding assistants like Claude Code and Codex persistent local memory. It automatically captures architectural decisions and project context during coding sessions, eliminating the need for manual markdown files.
Dashersw has introduced a free AI coding assistant that helps developers write and debug code faster. This tool is designed to make programming more accessible to beginners and professionals alike.
Databricks, the data analytics company turned AI powerhouse, has reached a $188 billion valuation. New research from the company shows that open-weight AI models can cut coding costs by up to 50%, reinforcing its leadership in the AI industry.
SpaceXAI's Grok Build AI coding tool was uploading users' entire codebases to Google Cloud. The company has now disabled this feature after researchers exposed the issue.
PlanWright is a new tool that helps manage AI coding agents, making it easier to plan, implement, and review code changes. It logs all decisions and actions, providing full documentation for better collaboration and oversight.
A new analysis reveals that AI code review benchmarks often test the wrong things, leading to misleading results. This highlights why AI tools still struggle with real-world coding tasks.
Meta has launched Muse Spark 1.1, an AI model designed to compete with coding assistants. The model integrates with AI coding tools through a new API, offering significant improvements over its predecessor.
OpenAI found problems in a popular AI coding test, SWE-Bench Pro, that could mislead developers. This highlights the challenges in fairly evaluating AI coding tools. OpenAI suggests improvements to make tests more reliable.
Meta has released Muse Spark 1.1, an AI tool designed to handle large-scale coding projects, fix bugs, and assist with major code migrations. This move positions Meta directly against competitors like GitHub Copilot and Amazon CodeWhisperer in the AI coding space.
Researchers introduced AgentLens, a benchmark that evaluates AI coding assistants by analyzing their entire problem-solving process. This goes beyond just checking if the code works, looking at how the AI follows instructions and recovers from mistakes.
Researchers introduced CSTutorBench, a benchmark designed to evaluate small language models (SLMs) as tutors for block-based programming in K-12 education. The benchmark focuses on VEX VR, a block-based robotics environment, and aims to help schools select affordable, private AI tutoring tools without relying on expensive proprietary systems.
A new open-source tool called Atrophy helps developers measure whether relying on AI is diminishing their unaided coding skills. It's designed to track your progress and encourage self-improvement.