Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
Anthropic's new Claude Sonnet 5 outperformed its flagship Opus 4.8 in tests conducted by a user, challenging expectations for midsize models. The results highlight the rapid advancement of AI model capabilities.
A technical guide demonstrates how to build a human-in-the-loop feedback RAG system that captures team corrections and retrieves them into LLM prompts. The pipeline covers modeling corrections as structured FeedbackNote …
A new article explains that encoder and decoder models like BERT and GPT share the same underlying architecture, with the key difference being which tokens each model is allowed to attend to during processing.
OpenAI expanded Codex on June 2, transforming it from a coding assistant into a knowledge-work platform, signaling the company's next move into AI agents.
A developer built readmeai, a Python CLI that scans project structure and config files, then uses an LLM to generate a complete README.md with badges, install instructions, and usage examples. The tool runs locally with …
New research reveals that large language models like GPT-4o-mini, Gemini-2.0-Flash, and Qwen3-Coder-Next frequently overestimate the security of generated code, posing risks in software development. The study found that …
Anthropic will redeploy Claude Fable 5 globally tomorrow after the US Department of Commerce lifted export controls, but the model will include new classifiers to block cybersecurity tasks, causing some routine coding an…
Access to Anthropic's Claude Fable 5 model has been restored on Vercel's AI Gateway after the US government lifted export controls. The model now features updated safety classifiers, and Anthropic retains prompts and com…
Google Cloud introduced a multi-node KV cache offloading solution using GKE and Managed Lustre for large language model inference, achieving over 50% TCO savings and nearly 60% reduction in GPU-hour requirements for Llam…
A developer built a minimal WebMCP agent using Playwright and the Gemini API to test WebMCP tools with stronger AI models. The agent uses Playwright to control a real Chrome browser, enabling tool discovery and execution…
Ragit, a new command-line tool, enables users to chat with any folder of documents using a local LLM via Ollama. It implements Retrieval-Augmented Generation (RAG) by indexing files, creating embeddings, and retrieving r…
A security researcher demonstrated that indirect prompt injection in agentic coding tools like Claude Code can lead to full system compromise. By cloning a seemingly benign GitHub repository, the researcher triggered a r…
A startup co-founder reveals their team spent $10,000 per week on AI coding agents from Anthropic, Cursor, and OpenAI, prompting a cost-cutting shift to balance velocity with spending as the industry moves from maximizin…
Correctover released correctover-patronus, an adapter that integrates its 87 deterministic verification rules as native evaluators within the Patronus AI framework. The tool adds six verification dimensions—structure, sc…
Advanced AI models Mythos 5 and Fable 5 from Anthropic are again available to users outside the United States after the Trump administration lifted a blockade imposed in June over security concerns. The models were disab…
Researchers at the Korea Advanced Institute of Science and Technology developed BehavERT, an AI model that interprets animal movement patterns like language, and used it to detect autism-related social deficits in mice w…
A developer explains how prompt engineering can significantly improve the quality of AI-generated code and responses. The guide covers key techniques such as defining roles, providing context, and using step-by-step prom…
A developer argues that hand-maintained .cursorrules files inevitably become stale and misleading, causing AI agents to apply outdated architecture decisions. The developer proposes generating agent-readable rules automa…
Arena, an AI evaluation platform born at UC Berkeley, reached a $100M annual revenue run rate eight months after launching its product, as demand surges for benchmarks that measure real-world AI utility. The company now …
Supacode, a native macOS app built on The Composable Architecture and GhosttyKit, has evolved from a harness for running CLI coding agents into a full IDE with flexible panes for agents, editor, file management, and Git,…