A critical vulnerability chain in LiteLLM, a widely deployed open-source AI gateway, allows attackers starting from a default low-privilege account to achieve full server takeover and code execution. …
A developer built Lynkr, a self-hosted LLM gateway, to reduce costs in Microsoft Agent Framework workloads. The gateway adds semantic caching, response compression, and model tiering to cut token usag…
Microsoft has released a new monitoring and observability integration for Azure OpenAI that uses OpenTelemetry to export logs, traces, and metrics to SigNoz, enabling developers to track model perform…
Lynkr, an AI gateway built for coding workflows, outperformed LiteLLM in cost efficiency across nine benchmark scenarios using the same backends—Ollama, Moonshot, and Azure OpenAI. Lynkr achieved a 53…
Microsoft's proprietary MAI Image 2.5 text-to-image model now ranks #3 on the arena.ai leaderboard, beating competitors including Stable Diffusion 3.5, DALL-E 3, and Ideogram 2.0 based on human prefer…
An engineer built OpenSecant, an AI-native resilient automation framework on Playwright, to address practical challenges in test automation. The framework uses a deterministic-first approach with loca…
A developer has built an end-to-end Retrieval-Augmented Generation (RAG) pipeline using LangChain, Milvus, reranking, and Azure OpenAI to reduce hallucination in large language models. The system retr…
LinkedIn automatically enabled a "Data for Generative AI Improvement" setting for most users, allowing the platform and its affiliate Microsoft to train AI models using members' public profile informa…
Based on the article, the local implementation of this Enterprise RAG system is fully functional, featuring pre-retrieval access control, citation-backed answers, and a specialized evaluation set, all…
Microsoft's Python Risk Identification Tool (PyRIT) is an open-source framework designed to automate red team testing of large language model (LLM) systems by chaining together targets, prompt convert…