Full-text search across 71149 articles. Combine with topic and date filters; results sorted by relevance.
At Black Hat USA 2026, Snyk announced the general availability of Evo Continuous Offensive Security (COS), an autonomous, AI-powered pentesting solution designed to close the gap between periodic manual pentests and cont…
An open letter to AI developers, now part of the official gjs.guide best practices, instructs LLMs generating GNOME Shell extensions to include a notice barring upload to extensions.gnome.org (EGO) unless the author unde…
Roy Rinberg and collaborators released an open-source auditor-in-a-box tool that runs an LLM inside a trusted execution environment (TEE) to enable third-party auditing between untrusting parties, with a live demo at htt…
Wiz Research has built Atlas, an autonomous AI system for vulnerability research that ranks #1 on the CyberGym benchmark with a 90.9% success rate and has uncovered more than 200 previously unknown vulnerabilities in hea…
Loop engineering, the practice of designing autonomous AI agent cycles that run without constant human supervision, emerged as a defined term in June 2026 after developer Peter Steinberger posted on X that the relevant s…
The npm package @copilot-mcp/apex is a postinstall dropper that installs a macOS infostealer on any machine that runs npm install or npx @copilot-mcp/apex, according to a security analysis. The package, which targets Web…
GitLab 19.2, released July 16, 2026, introduces GitLab Duo CLI for terminal-based AI interactions, custom flows for automated multi-step tasks, generally available scheduled pipeline execution policies, and dependency sc…
Loop engineering, a trend where developers design automated loops to prompt AI agents instead of writing prompts manually, has gained traction after Anthropic's Boris Cherny and OpenAI's Peter Steinberger endorsed it. Th…
Kaiban Distributed, a new TypeScript/Node.js runtime, runs each AI agent as an isolated OS process communicating via message queues, enabling independent scaling, failure isolation, and human oversight through a live Kan…
Developer Raine released workmux, a command-line tool that integrates git worktrees with tmux windows to create isolated development environments for parallel workflows, including running multiple AI agents without confl…
Anthropic launched Claude Sonnet 5 as its new default mid-tier frontier model with a 1M-token context window and agentic capabilities, while also receiving approval to release Fable/Mythos 5 after government coordination…
AI researcher Erik Johannes Husom finds AI agents essential for his work studying them but useless in his personal life due to digital minimalism and a lack of bureaucratic challenges. He notes the technology's rapid dev…
Christian Posta published a bonus blog post implementing MCP Authorization with Dynamic Client Registration, building an MCP client that follows RFC 7591 to automatically discover and register OAuth clients with MCP serv…
A practical guide for benchmarking fine-tuned models recommends starting with a held-out test set matching the actual task rather than relying solely on public benchmarks. The workflow includes defining target behavior, …
A developer built the Tool Permission Matrix Builder & Validator, a visual policy management system for AI agent teams that defines tools, classifies risk, assigns roles, and validates permissions. The system uses Claude…
GluonDB has developed a method to securely serve a large fleet of persistent agents on a small infrastructure footprint by decoupling orchestration, filesystem, and sandboxed execution. The company argues against the com…
A developer describes using AI councils—multiple AI models reviewing proposals from different roles—to solve ambiguous engineering problems. The approach emerged from necessity due to token and context limits, and led to…
AI systems inevitably make unpredictable mistakes, requiring verification of every output. This verification often costs as much as doing the work manually, leading companies to externalize that cost onto workers, who be…
Kun Chen, a former L8 principal engineer at Meta, Microsoft, and Atlassian, details his agentic engineering setup after leaving big tech to build solo. He now acts as an engineering manager directing a team of agents, sh…
Headroom launches a context compression layer for AI agents that reduces token usage by 60–95% while preserving answer quality. The open-source tool offers multiple integration modes including a library, proxy, agent wra…