Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
DeepSeek will launch its V4 series in mid-July with peak hour pricing that doubles token rates during designated periods, a first for the AI industry. The tiered pricing affects both V4-Pro and V4-Flash models, with peak…
Apple unveiled a rebuilt Siri AI at WWDC 2026, powered by Apple Foundation Models and a partnership with Google Gemini, emphasizing privacy through on-device processing and Private Cloud Compute. The move positions Apple…
Two weeks after the US restricted exports of Anthropic's Mythos and Fable 5 models, Chinese lab Zhipu AI released GLM-5.2 and Japanese startup Sakana AI released Fugu, both matching or surpassing Anthropic's performance …
A comparison of AI coding assistants Cursor, Claude Code, GitHub Copilot, and Windsurf across six real engineering scenarios evaluates their performance in 2026.
A new analysis argues that retrieval-augmented generation (RAG) pipelines frequently fail in production due to retrieval irrelevance and context poisoning, with enterprise implementations showing a 72% first-year failure…
A developer tested Qwen-AgentWorld-35B-A3B, a 35-billion-parameter model designed for agentic reasoning, and found it excels in state tracking and tool-use reliability. The model demonstrated disciplined 'check-then-proc…
SEO Score API has released an official Model Context Protocol (MCP) server that gives AI tools like Claude Desktop, Claude Code, Cursor, and Windsurf direct access to nine SEO tools, including audit, batch audit, backlin…
Artificial intelligence systems, particularly large language models, produce human-like language through associative patterns rather than consciousness, raising questions about whether AI mirrors the structure of the unc…
Mneme, a new open-source tool, governs AI-generated code by enforcing project decisions before the model writes a line. It reads existing architectural decisions and checks tasks against them, preventing architectural dr…
A developer released a JavaScript fundamentals collection called 'JavaScript By Example' to help both beginners and seniors refresh core concepts. The project provides concise examples covering values, variables, conditi…
Google Cloud will offer specialist AI models from SandboxAQ, called large quantitative models, through its marketplace, pairing them with Gemini to serve scientific fields like drug discovery and materials science. The m…
A developer discusses how AI crawlers and robots.txt policies are fragmenting the web's shared information environment. As websites selectively allow or block AI systems like ClaudeBot and GPTBot, retrieval access is div…
A senior software engineer argues that prompts are disposable while skills are infrastructure, drawing on frameworks from Dan Shapiro and Nate B. Jones. The engineer identifies Gherkin scenario quality evaluation as the …
A developer created a set of 8 reusable skill files for Claude Code that encode production React conventions for common features like auth flows, multi-step forms, and paginated tables. The skills, extracted from real Sa…
Meta has restricted its engineers from using Anthropic's Claude Code and OpenAI's Codex AI coding tools to protect proprietary AI training data and internal codebases from exposure. The policy, effective as of June 2026,…
Cockroach Labs' State of AI Infrastructure 2026 report reveals that 83% of engineering leaders expect AI-driven demand to cause data infrastructure failure within 24 months without major upgrades. The report warns that A…
A developer found that the risk of system prompt leakage in AI agents depends more on the underlying model than the prompt itself. In a small measurement with five different models, disclosure rates ranged from near zero…
HackerRank open-sourced its AI résumé screener, hiring-agent, revealing that the same résumé scores between 66 and 99 across runs due to LLM nondeterminism, not parsing errors. The volatility means a candidate can pass o…
A developer explains the inner workings of the ReAct (Reason + Act) pattern for AI agents, distinguishing between the message-level and state-level perspectives. The core of ReAct is not the prompt format but the agent's…
Databricks released `databricks-cost-leak-hunter`, a skill for the Claude Code Plugins marketplace that identifies cost leaks in Databricks workspaces. The skill enforces a strict architectural rule: the LLM never perfor…