Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
A developer built the same AI agent using Cursor, Claude, and OpenAI's new SDKs, finding that one implementation required only 9 lines of code, raising questions about efficiency and tooling choices.
AI bias compounds as models become more intelligent and autonomous, scaling historical inequities from training data, RLHF alignment, and cultural gaps into high-stakes decisions like loan approvals and resume screening,…
A wealth management assistant's evaluation suite focused on tool routing rather than answer correctness, allowing bugs to reach users. Adding answer-level evals with a three-layer pass criterion caught inconsistencies th…
A developer compared a general-purpose LLM (Claude) with a purpose-built AI SRE tool (Knox) for infrastructure discovery on a small stack of Linux VMs and a Kubernetes cluster. Claude produced a flat markdown report lack…
Anthropic released the Claude Agent SDK, revealing that the core agent loop is a simple while loop, demystifying AI agent operations. The SDK aims to make agent development more transparent and accessible to developers.
Anthropic released the Claude Agent SDK, a new tool that eliminates the need for developers to write custom agent loops for tool-using AI models. The SDK provides a pre-built layer that handles the while response.stop_re…
Many users are underutilizing Claude by treating it as a basic chatbot, missing its advanced features like Projects, Skills, and Artifacts that enable persistent memory and reusable workflows. By setting up a Project wit…
OpenRouter launched Fusion, a new API feature that turns a single prompt into a multi-model deliberation by analyzing it with a panel of expert models and synthesizing their responses via a judge model. The feature, pric…
A developer with 12+ years of Magento experience built a RAG-powered code review tool that understands project-specific patterns, not just generic advice. The tool indexes a codebase using tree-sitter for PHP parsing and…
A developer building a RAG pipeline for SRE runbooks shares seven vector search tips based on production experience. Key recommendations include using domain-specific embedding models like BAAI/bge-small-en-v1.5, impleme…
Elastic Security Labs released an open-source CI/CD Abuse Detector that uses Anthropic's Claude LLM to analyze pull-request diffs for malicious workflow changes in GitHub Actions, GitLab CI, and Azure DevOps. The tool ru…
Elixir and the Phoenix framework eliminate the need for separate services like Redis, Kubernetes, and Python sidecars by providing built-in concurrency, fault tolerance, real-time capabilities, and ML inference on the BE…
A developer reflects on how AI is reshaping software engineering, comparing it to past shifts like higher-level languages and Stack Overflow. The author argues that AI is the next abstraction layer, moving the bottleneck…
A developer reports that 80% of RAG system failures stem from poor document chunking, not the LLM or embedding model. A controlled study of 36 methods across 6 domains found content-aware chunking significantly outperfor…
A former EMS worker with a traumatic brain injury accuses the entire AI industry of abandoning its safety mission, claiming repeated attempts to present alignment concerns to organizations like LessWrong and Hugging Face…
A developer created a plugin called 'observer' for OpenCode that enables the DeepSeek-V4 language model to read images by calling a multimodal agent, allowing it to interpret error screenshots, charts, and visual designs…
A developer argues that pure vector search is insufficient for production RAG systems, as it fails on exact-match queries like product codes or legal citations. Hybrid search, combining BM25 sparse retrieval with dense v…
A developer used Claude Mythos to build BrandLM, a startup that audits brand visibility across AI answer engines like ChatGPT, Claude, Perplexity, and Google AI Overview, in one day. The tool generates reports showing ho…
Amazon CEO Andy Jassy reportedly raised security concerns about Anthropic's AI models with White House officials, leading the U.S. government to issue an export control directive that forced Anthropic to disable its Fabl…
Z.ai released GLM-5.2, its latest large language model, featuring a usable 1-million-token context window and two thinking-effort levels (High and Max), but no benchmark scores at launch. The model, the fourth flagship-t…