Full-text search across 4735 articles. Combine with topic and date filters; results sorted by relevance.
Cheap Chinese AI models from Moonshot, DeepSeek, and Z.ai are boosting American software companies by lowering costs and increasing competition, with open-weight models accounting for 55% of tokens flowing through Vercel…
The Pydantic team has released official skills for Pydantic Validation, Pydantic AI, and Logfire, available on Claude's plugin marketplace and across coding agents via the agentskills.io spec. The skills, maintained by t…
Anthropic's Claude Code Agent Teams, an experimental feature for coordinating multiple Claude instances, is off by default and requires setting CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS to 1, with Anthropic recommending 3 to …
Ruby on Rails is a strong fit for AI agents because of its token efficiency, predictability, and ecosystem ergonomics, according to an analysis by Martin Alderson, co-founder of CatchMetrics. Alderson found up to a 2.6x …
A developer who burned through their token budget running Claude Code and Codex found that local inference with open-weight models trades dollar costs for wall-clock and retry costs. Testing Qwen3-Coder-Next on a 64 GB m…
Writing toy software is a joyful and educational practice that helps developers understand systems deeply, according to a 2025 essay. The author argues that building small, non-production programs like a regex engine, OS…
A developer warns that the term 'agent' is being diluted, causing real engineering mistakes, and argues that most real agent deployments are narrow, purpose-built pipelines. The developer defines an agent as a system wit…
Postman's team found that coding agents are now the primary consumers of APIs, yet most API programs are not optimized for machine consumption. The company launched an AI-Ready APIs assessment to help organizations measu…
LangChain, LangGraph, LangSmith, Langflow, and other 'Lang' tools are often confused. A developer's guide clarifies the ecosystem: langchain-core is the foundation, langchain offers batteries-included agents, langgraph p…
A developer building an MCP server found that 52% of 2,181 remote MCP endpoints scanned in April 2026 were completely dead, with only about 9% fully healthy. The failures stem from issues around the protocol, such as log…
Together AI announced a strategic partnership with Moonshot AI to become the launch platform for Moonshot's open-weight models, starting with Kimi K3, a 2.8 trillion parameter sparse Mixture-of-Experts model with native …
Microsoft has added an Azure Container Apps (ACA) provider to its open-source Conductor agent framework that relocates an agent's execution loop from the user's local machine into a Hyper-V isolated container in Azure, p…
MCP gives agents access to every tool but does not connect the work, preserve what sessions learn, or give humans and agents a shared workspace, according to an analysis by the author. The five things a workspace still h…
The viral dithered website effect, a design trend featuring low-resolution black-and-white animated backgrounds, can be built for under $1 using AI tools like Nano Banana Pro for image generation and Seedance 2.0 for vid…
MotherDuck introduced Guides, a context layer for AI agents that lives in the data warehouse, reducing agent query errors by ~99% (from 302 to 1) and lowering costs by ~55% on the DABStep agentic analytics benchmark. Ava…
Hugging Face was hit by an autonomous AI-driven intrusion built on OpenAI's most advanced released model plus an unreleased one, but the company had to defend its network using an open-source Chinese model, GLM, because …
1,134 employees from OpenAI, Anthropic, Google, and Meta signed an open letter titled 'Pacing the Frontier' asking the US government to develop tools to slow frontier AI development if needed, triggered by OpenAI's rogue…
NPMScan has launched a public MCP server that allows AI coding agents to query npm package metadata, versions, install scripts, maintainers, known vulnerabilities, and recent security advisories. The server is read-only …
Adding a single skill to an LLM agent reliably improves task performance, but by the time a fourth skill is active, the cumulative gain shrinks to a fraction of what two skills produced, according to the SkillsBench benc…
A new supply chain attack called 'slopsquatting' exploits AI hallucinations by tricking developers into installing malicious packages that LLMs invent, with research across 500,000 code samples and 16 LLMs showing a 19.7…