Full-text search across 25117 articles. Combine with topic and date filters; results sorted by relevance.
A developer behind Auten documented why Claude Code's built-in computer-use server is absent from /mcp on Linux, Windows, Team/Enterprise seats and cloud-provider setups, explaining that Anthropic's native feature is lim…
GeekyAnts published a technical breakdown of an MCP-powered QA agent that places Anthropic's Model Context Protocol between LLM clients and engineering tools like Playwright, using the MCP TypeScript SDK v2 and Zod schem…
A developer built Forkpath, an open-source alternate-history explorer that takes a one-sentence premise and generates a branching timeline of events, each fork assigned a likelihood. The TypeScript app runs locally, stor…
Hugging Face released AnyLanguageModel 1.0, a drop-in replacement for Apple's Foundation Models framework that lets Swift developers swap `import FoundationModels` for `import AnyLanguageModel` and run the same session c…
Okta took Agent SSO, Agent-to-Agent Connections and Resource Access Certifications to general availability on September 22, 2026, with an ecosystem of more than 25 partners including Anthropic, Cloudflare, Keycloak and W…
Microsoft Corp. on Oct. 19 introduced security controls aimed at what Microsoft Security executive vice president Hayete Gallot called the "agentic insider," cutting back what an AI agent may do as its assessed risk clim…
Zillow launched a connector on October 19 that brings home listings, maps and affordability tools into Anthropic's Claude, keeping Zillow's tour, agent-connection and financing pathways inside the conversation. The launc…
Taco 0.1.0, an alpha proof-of-concept lossless compressor released on 2026-10-19, folds and unfolds a 3,672-byte English text sample to 648 bytes with an identical SHA-256 hash (2fab1ef7a1c70cd4e39ddfd88a8d66389ae07a4031…
AI models have exposed exploitable mathematical flaws in two post-quantum cryptography schemes, HAWK and Classic McEliece, according to Conor Deegan, co-founder of Project Eleven, who spoke on October 19, 2026. Anthropic…
A single Chinese-speaking hacker used AI agents to attempt breaches of more than 1,200 e-commerce sites across the United States, Canada, Australia and Japan between September 25 and mid-October, with roughly 10% succeed…
Zed released version 1.24.2 on October 14, adding the ability to drag an existing terminal tab into the AI Agent Panel and convert it into a live Terminal Thread that preserves its shell history, working directory, and r…
Harvey customers can now access Midpage's AI legal research library of U.S. case law, statutes, regulations and agency materials directly inside Harvey through a new MCP connector, the two companies announced. The connec…
OpenTokenMini launched as a free and open source tool that measures, analyzes and fixes what AI agents spend, with integrations for open models, OpenAI and Anthropic. The project is installed by cloning its GitHub reposi…
California's Delete Act now requires registered data brokers to access the DROP deletion platform and process residents' opt-out requests at least once every 45 days as of Aug. 1, 2026, according to the California Privac…
E. O. Kahya, a co-author of both original papers, used Anthropic's Claude Opus 5.5 to re-derive step by step a published one-loop quantum gravity calculation of the graviton correction to a massless, minimally coupled sc…
OneGlanse has launched as a self-hostable, MIT-licensed tool that tracks how brands appear in AI-generated answers from ChatGPT, Perplexity, Gemini, Claude, and Google AI Overview. Unlike API-based trackers, OneGlanse co…
Bifrost, the open-source AI gateway from Maxim AI, and Cloudflare's Agents SDK independently replaced large MCP tool catalogs with direct code generation, converging on an architecture that cuts input token consumption b…
A Chinese-speaking hacker used autonomous AI agents to breach websites belonging to more than 100 companies, including Deere, SharkNinja and Cummins, in a campaign that began on 25 September, according to cybersecurity r…
A Chinese-speaking hacker used AI agents running on the open-source Cairn platform to attempt break-ins at more than 1,200 e-commerce websites across the US, Canada, Japan and Australia, succeeding at roughly 10% of task…
Elastic Security Labs researchers Jia Yu Chan and Daniel Stepanic reported that a fake Web3 accelerator called Apex Accelerator, tracked as REF8801, used malicious npm packages @apexacc/cli and @apexacc/audit to deliver …