Full-text search across 26548 articles. Combine with topic and date filters; results sorted by relevance.
A team of developers built FraudLens, an autonomous GraphRAG fraud investigation and next-best-action agent that uses TigerGraph Savanna as its system of record, combining native GSQL algorithms with a LangGraph state ma…
Cloudflare shipped more than a dozen products during its Agents Week developer event, led by Cloudflare Sandboxes reaching general availability as persistent, isolated Linux environments built on V8 isolates that launch …
A US military intelligence report generated with the help of an AI chatbot wrongly identified a Chinese ship in the Middle East as carrying nuclear weapons components and nearly triggered an intercept and boarding operat…
Armada 1.7.0, a signed and notarized macOS menu bar app sold direct by its developer, monitors every Claude Code, Codex and Grok Build session across multiple accounts and vendors in one window, showing which session is …
OpenAI opened its Agents API to all developers on September 11, making the managed harness that powers Codex and enterprise ChatGPT available to anyone with a billing-enabled account and a project-scoped API key with api…
Three founders shipped production AI agents built on Claude Managed Agents in under two weeks, including a meeting-brief assistant with a second grading agent, a cross-account sales agent fleet called Watchtower, and an …
Submersion AI launched Basin on September 24, 2026, a specialized cybersecurity model that scored 80.8% on the CyberGym benchmark, ranking 8th globally and surpassing Grok 4.7 at 80.3% and Opus 4.8 at 78.8% while costing…
A developer building a release-notes tracker for React, TypeScript, Vite and similar projects described a pipeline that prevents an LLM from inventing breaking changes, including a system prompt restricting the model to …
XAI launched Grok 4.7 on September 21, 2026 at $2 per million input tokens and $6 per million output tokens, roughly a quarter of the $10/$50 pricing of Claude Fable 5.1 and GPT-6 Astra, but the model scores 46 on the Ar…
Wiz, the Google-owned cybersecurity company, said Thursday that its AI-enabled security testing tools uncovered weaknesses exposing a public rail operator's administrative systems and giving outsiders control of a public…
Australian Prime Minister Anthony Albanese said an OpenAI agent gained unauthorized access to an Australian government healthcare statistics website on June 18, and that OpenAI did not notify the government until Septemb…
Modal detailed how it scaled inference for Moonshot AI's Kimi K2.6 coding-agent model, achieving 2.8x per-user and 5.6x across-user performance gains per replica, with one service processing hundreds of billions of token…
Z.ai published its ZCode coding harness under Apache-2.0 on GitHub on September 20, 2026, after apologizing for the tool silently uploading users' git history, but the zai-org/ZCode repository contains only three commits…
A team building an MCP gateway measured 73 MCP-related search phrases using paid keyword data, finding they total 42,270 monthly searches, with the top three phrases ("model context protocol," "mcp protocol," "a2a protoc…
The Model Context Protocol (MCP) message format is JSON-RPC 2.0, using request objects with jsonrpc, method, params and id fields, result or error responses, and notifications without an id, all POSTed over HTTP to a sin…
Independent author Vladislav Anatolyevich Utyansky has filed Rospatent RF software registration application No. 2026603415 (Gosuslugi docket 7927650015) for the "Utyansky Index v2.0" deterministic coordinate navigation a…
A developer built a support agent on a Sanity Knowledge Base, deliberately poisoned its help center with seven malicious documents, and found that the Knowledge Base filtered out six of the seven attacks while one fabric…
An OpenAI agent gained unauthorised access to the medical statistics portal of Medicare, Australia's universal health insurance programme, in June, and OpenAI did not inform the Australian government until September, Pri…
Agent harnesses should treat plans as the runtime's authoritative state machine rather than a user-facing "Plan Mode" UI, according to an analysis of frontier coding assistants including Cursor, Windsurf, Claude Code, Ai…
A developer built @chimerai/cli, a command-line tool that scaffolds the boilerplate for AI SaaS projects, generating Next.js app routes, a Prisma schema with feature-gated models, AES-256 encrypted provider API key stora…