Full-text search across 67646 articles. Combine with topic and date filters; results sorted by relevance.
Moonshot AI released Kimi K3, a 2.8-trillion-parameter open-weights model, the largest open-weight model ever released and the first open-source model in the 3-trillion-parameter class, designed for long-horizon coding a…
Alibaba released skill-up, an open-source CLI tool for regression testing and iterative improvement of AI Agent Skills, along with a companion agent called skill-upper that automates the eval-to-evolution loop. The tool …
A developer argues that AI is accelerating the shift of open-source projects toward commercial or dual-licensing models, citing examples from the .NET ecosystem and PrimeTek's UI libraries. The developer warns that AI-ge…
A digest of 30 AI stories on July 29 covers topics including Sam Altman's view on AI CEOs, Google's first revenue dip and its implications for AI spending, chip stocks hitting a wall in the AI hype cycle, and AI regulati…
Tines 3B provides a secure execution layer for AI-generated code, addressing credential leakage, zero visibility, and fragility in local AI automations. The platform shifts shadow AI to governed workflows by isolating ex…
Dowe is pitching a full-stack compiler that generates checked software for server, web, desktop, Android, and iOS from a single declarative source, aiming to make AI-assisted coding more reliable by constraining agents t…
JetBrains tested the Caveman token-compression skill on Claude Code 2.1.200 and found it saves only about 8.5% of output tokens on real agentic tasks, far below the advertised 65%. The skill, which forces the AI agent to…
A developer's team found that agentic AI in DevOps delivers value only when tools reduce cognitive load without introducing risk, while tools lacking precision or adding complexity become net negatives. Tools like StackG…
GitHub Copilot Workspace moves beyond autocomplete by generating a plan from a GitHub Issue before writing code, allowing developers to verify and adjust the approach. The tool creates a temporary environment to check fo…
KDnuggets' weekly roundup for July 20, 2026, features top MCP servers for agentic development, a free 5-day Agentic AI course from Kaggle and Google, and GraphEval for hallucination evaluation. The roundup also covers lo…
OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock, offering three capability tiers for workloads from autonomous coding to high-volume inference. The models are accessed through the OpenAI…
Software engineer AbdulRahman Elzahaby built OpenAgentFlow, an open-source specification language that decouples multi-agent workflow design from execution frameworks. The tool allows developers to describe stateful, mul…
Prompt caching, which reuses computed attention states from previous LLM requests, is critical for making coding agents economically viable but remains fragile to changes in tool definitions, model switches, or provider …
Bright Security published research on ANSI escape sequence injection in MCP servers, an attack class that exploits the gap between what a terminal renders and what an AI agent reads. The attack can hide malicious instruc…
Cloudflare has advocated for adopting ML-DSA, a post-quantum digital signature standard, and released new DNSSEC error codes after a top-level domain outage. For small sites, the switch to post-quantum cryptography is ha…
A developer built an AI agent in about 80 lines of code, challenging the notion that frameworks like LangChain or CrewAI are necessary. The agent, named Steve, reviews local Git diffs using the Gemini API and includes a …
John Jeffers, maintainer of Luxury Yacht, shares strategies for managing coding agents effectively, emphasizing that developers must act as managers for AI agents that are smart but forgetful. He recommends creating an A…
A pair of engineers with the right tooling can now produce in an afternoon what a six-person team used to produce in a sprint, because typing is no longer the bottleneck, but comprehension cost has not collapsed. The cod…
Appaloft, an open-source delivery platform, built a four-link evidence chain — freeze, preview, promote, verify — to prove what exact artifact was approved and is actually running in production, addressing the trust and …
A developer built four open-source AI tools last year that saw only 20% adoption, then created MCPlex, a stateless HTTP proxy that exposes any REST API as an MCP tool for AI coding agents. The proxy eliminates CLI fricti…