Full-text search across 68181 articles. Combine with topic and date filters; results sorted by relevance.
Newsjack released 18 open-source PR skills that can be installed into Claude, turning the AI into a PR associate that monitors news overnight and produces pitch-ready briefs. The skills include a journalist database with…
AI accelerates software development so fast that it can produce legacy code—complex, hard-to-understand systems—in weeks rather than years, warns engineer Federico Pereiro. While AI boosts speed and can detect security i…
A GitHub Gist by lukewilson2002 proposes a repo-local Markdown documentation system using AGENTS.md and a docs/ directory to provide predictable context for human developers and AI coding agents. The system aims to reduc…
The Ethereum Foundation's Protocol Security team reported that AI agents successfully identified real vulnerabilities in protocol code, including a remotely triggerable panic in libp2p's gossipsub component (CVE-2026-342…
OpenCode, an MIT-licensed terminal-based AI coding tool, reached 7.5 million monthly active developers and claimed the top spot in LogRocket's July 2026 AI dev tool power rankings, surpassing Cursor. Cursor's market shar…
XAI released Grok 4.5 with a $6 per million output token price, positioning it as a cost-effective option for coding agents. The model achieves competitive benchmark scores, notably using far fewer output tokens than riv…
Google AI Studio added an 'import from GitHub' feature to its Build mode, allowing developers to transform a GitHub repository into a runtime-compatible app for iteration and deployment. The feature, announced by Google …
OpenAI's audit of SWE-Bench Pro found that roughly 30% of the benchmark's tasks are broken, with issues including overly strict hidden tests, underspecified prompts, and low-coverage tests. The findings raise concerns ab…
Onboard-CLI, an open-source tool that uses LLMs and AST parsing to visualize and analyze codebases, has been released. The CLI generates interactive dependency graphs, detects architectural drift, and supports multiple p…
Anthropic announced the Claude apps gateway for AWS, a self-hosted control plane that gives organizations centralized management of access, cost, and policy for Claude Code and Claude Desktop. The gateway integrates with…
Anthropic suspended access to its Fable 5 and Mythos 5 models on June 12 after the US government applied export controls, and Alibaba banned all Anthropic products effective July 10, designating its own AI coding platfor…
Mana Jampala, a 12-year-old founder in British Columbia, launched Voxa, an AI-powered receptionist that helps small businesses answer calls and manage appointments. The product, built using AI coding tools, is already ha…
A developer tested four Chinese AI models—DeepSeek, Qwen, Kimi, and GLM—across coding, reasoning, creative writing, and Mandarin tasks. DeepSeek V4 Flash emerged as a top pick for its balance of performance and cost at $…
Microsoft has begun routing AI prompts in Excel, Outlook, and GitHub Copilot from OpenAI and Anthropic models to its own in-house MAI models, with tens of thousands of weekly prompts already completed by MAI. The move, c…
ConnectiveOne and Evergreen co-founder Sergii rebuilt the software development lifecycle around role-based AI agents, achieving a 300% increase in delivery speed. By treating agents as new hires with narrow scopes, versi…
A developer argues that as AI agents improve at reading complex infrastructure, explicit infrastructure-as-code becomes more valuable than black-box abstractions. Comparing Terraform on AWS versus Cloudflare, the develop…
Anthropic's Claude Fable 5 model refused mid-tool-call on 11 of 44 coding-agent turns in a Synthorai evaluation, on mundane tasks such as fixing a config default. The refusal truncates tool arguments mid-stream, but the …
At the AI Engineer World's Fair in San Francisco, the central theme was that AI models are no longer the bottleneck; instead, human attention has become the scarce resource, as teams adopt multi-agent loops and software …
Google researchers Sanjay Ghemawat and Amin Vahdat proposed a 'logical monolith' architecture to decouple code logic from deployment, but critics argue it ignores technical heterogeneity, fault isolation, and organizatio…
A developer built a complete AGENTS.md file for a URL shortener API in Python, demonstrating how the file guides AI coding agents by specifying setup, test, structure, conventions, and guardrails. The hands-on tutorial s…