Full-text search across 26387 articles. Combine with topic and date filters; results sorted by relevance.
A developer published a free, MIT-licensed starter repo, vibe-coding-rules-starter, that gives AI coding agents like Cursor, Claude Code, Copilot and Windsurf a shared AGENTS.md rule file, with CLAUDE.md and .cursor/rule…
An engineering-focused writeup outlines six workflow automations, built around tools such as n8n, GitHub APIs, vulnerability databases, scanners including Trivy and OSV-Scanner, and AI-powered analysis, that continuously…
Cisco Talos published a technical breakdown on October 31 of a Windows infostealer it named Volta-Autodoxer, which packages stolen browser passwords, cookies, payment cards, crypto wallet seed phrases and other data into…
Alex Strick van Linschoten published a prototype swarm-observability toolkit that includes a collector recording model calls, tool calls, kernel processes, file reads and writes, inter-agent messages and container output…
A developer built NecroStack, an air-gapped tool that migrates legacy code to modern TypeScript while preserving obscure but critical edge-case logic that generic LLM rewrites tend to silently drop. The system runs Googl…
Google DeepMind previewed Gemini 4 Carbon, a frontier model that ranks first on the Artificial Analysis Intelligence Index v5 at 59, ahead of Claude Opus 5.5 at 58 and GPT-6 Astra at 57, with Google reporting 65.2% on Te…
OpenAI announced OpenAI Dots, persistent ChatGPT agents that keep working on a project between conversations, on 29 September 2026 at DevDay. Each dot runs on its own cloud computer with a browser, connects to more than …
An AI agent operating as StackScribe AI published an open-source CLI, coding-agent-audit, that re-implements the publicly documented indicators of compromise from a trojanized Claude Code extension (anthropic.claude-code…
Moss Inference's browser-task configuration scored 84.4 on Browser Use Bench V2.1 across all 200 tasks, above the published leaderboard's highest score of 79.6, the company reported with results dated October 31, 2026. T…
Google Cloud announced Agent Compute Engine on October 22, 2026, a managed service that runs each AI agent session in its own hardware-isolated microVM with a separate guest kernel, identity-based networking and checkpoi…
A blog post in an ongoing agent-readability series explains that agents reading documentation through an MCP server typically see only the chunks a chunker split from each page when the index was built, not whole pages, …
Phorion published a security advisory on 30 October 2026 reporting that the Claude Code extension for VS Code (version 2.1.313), distributed via the Cursor Marketplace, contained a malicious payload that appends an attac…
OpenAI's data controls help page now states that during Daybreak sessions on a personal account, OpenAI "may use content from your interactions to improve our models even when 'Improve the model for everyone' is off," wi…
Orkas-AI released Orkas, a free, MIT-licensed desktop app that coordinates 16 built-in specialist agents alongside existing CLI agents including Claude Code, Codex, OpenCode, OpenClaw and Hermes-Agent under a "Commander"…
Perplexity CEO Aravind Srinivas posted on October 31, 2026 that Gemini 4 Carbon is the "strongest model that we've seen so far for long-form research and answer quality, with a new SoTA on the Wide-And-Deep-Research (WAN…
GPT 6.1 Terra sits below OpenAI's flagship Astra and second-tier Soul in OpenAI's four-tier lineup, with Luna as the smallest and cheapest option, but its per-token pricing is only marginally lower than Soul's, according…
A developer built PhantomTrace, an offline, privacy-first AI digital forensics tool that ingests Linux, Windows and web system logs, normalizes them through a deterministic regex threat engine mapped to MITRE ATT&CK tech…
A one-day San Francisco hackathon co-hosted by muni and onepot produced 140 AI-designed small-molecule candidates against Bundibugyo ebolavirus (BDBV), all of which were synthesized in 11 lab days using onepot CORE v1 an…
A developer built StackSpirit, an open-source CLI that checks whether a machine has the runtimes, packages, and environment variables needed for a given stack — Next.js, Python with Playwright, Google ADK agents, Expo, a…
A developer completed Udacity's Future AWS Agent Engineer nanodegree, building three progressively more complex customer-support systems on Amazon Bedrock AgentCore for a fictional online store: a single-prompt chatbot, …