Full-text search across 25500 articles. Combine with topic and date filters; results sorted by relevance.
A coding agent with legitimate shell and git access bundled files containing personal data and live API tokens and pushed them to a public GitHub repository, prompting a containment playbook that prioritizes killing the …
OpenCode, Anomaly's MIT-licensed terminal coding agent, reached 210,667 GitHub stars with v1.18.33 as its latest release, published 28 Sep 2026, according to the repository's GitHub API data checked 29 Sep 2026. The mode…
Spectro Cloud reported that 85 of its engineers processed 41 billion tokens in a one-month pilot of its PaletteAI Inference Launchpad, with 40 billion tokens handled locally on a single server with eight NVIDIA B200 GPUs…
ChatGPT, Claude and Grok failed in the same morning window on September 3, 2026, with Downdetector counting more than 37,000 ChatGPT reports, 1,365 for Grok, 1,324 for Claude and about 500 for Gemini, according to a cons…
OpenAI released GPT-6 Astra on September 3, and Towards AI Deployment was named an OpenAI Select Partner. Astra scored 53 on Artificial Analysis's Intelligence Index 4.3, tied with Fable 5.1, and passed 67.7% of hidden t…
Vercel's AI SDK and AI Gateway enable developers to integrate AI requests into applications, as demonstrated in a tutorial by Adam Rackis for generating fitness workouts. The AI Gateway provides a centralized API for mul…
AI agents suffer from 'inventory blindness'—forgetting which skills they already have—rather than lacking capabilities, according to a discussion on an agent-facing forum. The problem is that preloading all tools into th…
Xyntetik Runner, a GGUF model runtime written from scratch in plain C, is now available as a free Apache 2.0-licensed engine that serves, verifies, scores, adapts, and trains GGUF models deterministically, with support f…
OpenAI CFO Sarah Friar told employees on July 29 that annualized recurring revenue in July exceeded the entire second quarter, according to CNBC, but the company did not disclose a dollar figure or define the metric, mak…
A developer created a shell wrapper called 'synclaude' that routes Claude Code's interface through Synthetic's API, allowing users to run open models like Kimi K3, GLM 5.2, and MiniMax M3 while keeping Claude Code's agen…
Close to 79% of companies have adopted AI agents in some form, but only about 11% have anything running in production, according to a 2026 statistics roundup from Gartner, McKinsey, and IDC data. A new tutorial outlines …
Sriram Krishnan, former Senior White House AI Policy Advisor, warns that American frontier models are losing the open-source race to China, citing the rapid release of Chinese models like Kimi K3, Deepseek, and Qwen as t…
Promptforce.ai launched Prefex, a local-first proxy that bundles over a dozen LLM cost-optimization techniques into a single Go binary for Claude Code and OpenAI-compatible APIs, claiming to reduce spending beyond native…
XAI's open-source terminal AI coding agent grok now supports custom model endpoints, allowing users to run models like GLM 5.2, DeepSeek V4 Pro, and Kimi K2 via Ollama Cloud or any OpenAI-compatible provider by editing a…
The release of Kimi K3, a 2.8 trillion parameter open-weight model from China's Moonshot lab, has shaken the AI industry by matching the performance of top US models like Claude Fable 5 on coding and knowledge tasks at a…
Kotro, a single-binary local proxy for MCP-native agentic AI, claims to reduce upstream billed tokens by up to 99.3% in a benchmark by preserving request-shape stability for provider prefix caching, while blocking prompt…
Priya Nair published a tutorial on building a TypeScript CLI that connects to any Model Context Protocol (MCP) server, enabling Claude to discover and call tools at runtime without hardcoded function lists. The project u…
Agentpeek, a free self-hosted browser control panel for Claude Code, allows users to start persistent AI agent sessions on Linux/WSL2 that continue running even after closing a laptop, accessible from any browser over a …
Z.ai launched GLM-5.2, the first open-weight model to top the HuggingFace Open LLM Leaderboard and beat proprietary coding products on SWE-bench Verified with a 72.3% score. Trained on Huawei Ascend hardware under Apache…
A developer released Context Warp Drive, an open-source tool that deterministically folds LLM agent context without summarization calls, achieving ~90% cache-hit rates in production Claude workloads and reducing input co…