Full-text search across 33840 articles. Combine with topic and date filters; results sorted by relevance.
A $120 million exploit of Nexus Protocol, which had passed three AI-powered code audits, reveals a new cybersecurity battleground where AI tools accelerate both defense and attack. Attackers are using the same AI models …
Anthropic's Claude Code introduced deterministic multi-agent orchestration workflows, enabling developers to script parallel agent execution, fan-out, reduce, and synthesis patterns. A 130-line workflow example demonstra…
Business Insider reporter Grace Kay used a ChatGPT prompt shared by OpenAI CEO Sam Altman on X to build a fully functioning website in under two hours, despite having no coding experience. The prompt asked ChatGPT to pla…
An engineer explores the concept of AI generating executable binary code directly instead of using high-level programming languages, highlighting potential performance gains and hardware-specific optimizations but also s…
A developer who ignored CLAUDE.md for two months discovered that writing a proper project-memory file dramatically reduced correction cycles with Claude Code. CLAUDE.md is plain Markdown loaded at every session start, gi…
Google Cloud's Gemini Enterprise Agent Platform introduces Agents CLI skills that let developers automate the entire agent development lifecycle—setup, build, deploy, govern, evaluate, and publish—without leaving their c…
A data scientist evaluated 10 AI coding models across 5 tasks, finding that DeepSeek-R1 scored highest at 9.4 but cost $2.50/M tokens, while Qwen3-Coder-30B offered the best balance at 8.8 and $0.35/M tokens. The analysi…
A developer on Linux Mint found that the Codex extension in VS Code failed to load its interface due to plugin sync failures with ChatGPT and GitHub, caused by broken IPv6 routing. Disabling IPv6 via NetworkManager resol…
OpenAI endorsed the European Commission's voluntary Code of Practice on Transparency of AI-Generated Content on June 11, 2025, committing to use provenance tools like C2PA Content Credentials and SynthID watermarks to co…
Spec-Driven Development (SDD) is a workflow that moves through five phases—requirements, design, tasks, implementation, and validation—each producing reviewable artifacts to reduce ambiguity before code changes. The appr…
A senior software engineer warns that AI coding agents, while boosting productivity, erode developers' understanding of their own codebases by breaking the feedback loop between writing and comprehension. The hidden cost…
Microsoft's Visual Studio Code now supports using locally hosted LLMs for chat, tools, and MCP servers via a new 'air-gapped' mode, enabling offline AI workflows without GitHub sign-in. Users can integrate models like th…
Anthropic released dynamic workflows for Claude Code that let the AI write and execute its own multi-agent orchestration scripts on the fly, addressing agentic laziness, self-preferential bias, and goal drift by spawning…
Agent Trace, an open specification for tracing AI-generated code, was released as an RFC in January 2026. It provides a vendor-neutral format to record AI contributions alongside human authorship in version-controlled co…
Microsoft released FastContext, a system that trains a dedicated explorer subagent to handle repository exploration for coding agents. By offloading read-only searches and returning compact file-line citations instead of…
Developers are increasingly switching to local LLMs for coding tasks, with two Hacker News threads (1,260 and 1,350 points) confirming local models are now viable. The guide compares self-hosted inference (Ollama, llama.…
Moonshot AI released Kimi K2.7-Code, a coding-focused agent model with 1 trillion total parameters and a 256K context window, aimed at multi-step software engineering tasks. The Beijing lab positions the open-weight mode…
Coding agent sandboxes address host compromise but not credential authorization, leaving agents with high-scope tokens that can push to protected branches, deploy infrastructure, or read secrets. The real risk is authori…
Anthropic, OpenAI, Cognition, Sierra, LangChain and leading practitioners have jointly developed a canonical standard for building production-grade agentic products, codified in a new open-source repository. The standard…
MoonieCode, a minimal AI coding assistant built in 393 lines of C++23 that communicates with Claude via HTTP requests. Its core logic is a single while loop that sends user prompts as JSON to an LLM API, then handles two…