Celebrating its first anniversary, the Agent-to-Agent (A2A) protocol is fostering an ecosystem where autonomous AI agents securely collaborate and delegate complex tasks.
Researchers leveraged an OpenAI reasoning model to assist physicians in diagnosing rare genetic diseases in children, leading to 18 new diagnoses in previously unsolved cases.
TypeScript 7.0 Release Candidate is here, marking a significant milestone as the entire codebase has been ported to a new, bootstrapped foundation.
This article explores methods for benchmarking open AI models using custom tooling to determine if their 'agentic' capabilities meet specific requirements.
This article delves into methods that aim to surpass LoRA, the widely adopted fine-tuning technique, for optimizing Large Language Models.
OpenAI details how GPT-5.5 Instant significantly enhances ChatGPT's health and wellness responses through improved reasoning, context, and physician-informed evaluations.
Claude Code introduces `CLAUDE.md` files, skills, hooks, rules, and subagents, offering developers granular control over AI agent behavior and workflows.
Anthropic provides an update on "Project Fetch," detailing the second phase of their frontier red teaming efforts focused on AI safety and security research.
Claude Code introduces support for artifacts, allowing developers to manage and utilize persistent outputs and intermediate files within their AI agent workflows.
Discover innovative techniques for animating images in three dimensions, dynamically controlled by user scroll interactions.
This article explores the concept of "MosaicLeaks," examining whether AI research agents can maintain confidentiality and keep sensitive information secret.
pnpm's latest minor release introduces a --dry-run option for installs, Node.js package map generation, and improved SBOM capabilities.
