Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
Meta paused its employee data-tracking program after an incident exposed sensitive information, including private conversations and performance reviews, to the entire company. The Model Capability Initiative, which colle…
A developer created a repository that enables Cursor to use the Claude Chrome extension to analyze the currently selected browser tab and return the response to Cursor for code editing. The tool uses macOS Accessibility …
A developer argues that backend engineers must shift from simply calling AI APIs to designing production-ready AI systems. The post outlines a structured approach with input, orchestration, and output layers, emphasizing…
A developer outlines a method for generating synthetic enterprise datasets that preserve real business relationships, addressing the challenge of obtaining operational data for AI systems. The approach involves designing…
A developer identifies three common reasons AI loops fail, none of which are the AI's fault: the input gap (failing to provide new inputs), the perfection death spiral (over-optimizing prompts before the loop is stable),…
A new guide maps five distinct RAG architectures for production systems, from naive RAG to advanced layered designs, explaining when to use each to avoid confident wrong answers at scale. The article provides implementat…
OpenAI updated GPT-5.5 Instant on June 24, improving its ability to understand user intent, maintain context across conversation turns, follow multi-part constraints, and provide better shopping and local-business recomm…
A Korean developer analysis revealed that Claude Code's 'Extended Thinking' text is a 600-character encrypted signature, not the model's reasoning, making agent audits impossible. Meanwhile, Anthropic's Slack beta for Cl…
In a podcast episode of complexity.fm, Bas Steins and Michal Martinka discussed why Python developers are adopting Rust for tooling like Ruff, uv, and Polars, citing Rust's strictness and compiler guardrails. They also a…
Anthropic accused Alibaba of running 25,000 fake accounts to steal nearly 29 million conversations from its Claude AI model, marking the largest known distillation attack. The accusation, detailed in a letter to the Whit…
Anysphere, the company behind the Cursor code editor, has trained its own frontier AI model called Composer 2.5 on Qwen 2.5 Coder using novel reinforcement learning techniques, enabling it to compete with GPT-5.5 and Opu…
Y Combinator CEO Garry Tan released G Stack, a CLAUDE.md configuration that equips AI coding agents with 23 specialist roles and 8 power tools to function as a virtual engineering team. The tool, installable in Claude Co…
GLM 5.2 from Zhipu AI outperforms Anthropic's Claude Opus 4.8 in UI generation tasks including 3D scenes, dashboards, landing pages, and mini games, while costing up to 10 times less. The comparison reveals that GLM 5.2 …
Anthropic's Claude Code introduces /goal and /routines commands that enable autonomous, scheduled workflows. The /goal command keeps Claude running until specific completion criteria are met, while /routines allows users…
Developers can now run Zhipu AI's GLM 5.2 model inside Anthropic's Claude Code coding environment by routing API calls through OpenRouter, using the ANTHROPIC_BASE_URL environment variable to point to OpenRouter's endpoi…
AI agent failures often stem from poor context management rather than model limitations. Static context loads fixed information every session, while dynamic context retrieves data on demand, balancing token efficiency an…
Google's AI coding guide defines a spectrum from vibe coding to agentic engineering, helping developers choose the right level of AI autonomy for their projects. The spectrum ranges from low-autonomy AI assistance for si…
Zhipu AI released GLM 5.2, a 744B parameter open-weight mixture-of-experts model that rivals Claude Opus in coding and visual design quality at lower inference cost. The model's MoE architecture activates only a subset o…
Zhipu AI's GLM 5.2 uses Index Share, a technique that reuses sparse attention indexers across four layers, reducing compute operations by 2.9x at 1M token context. This optimization makes long-context inference more affo…
Google's Gemma 4 31B outperforms Alibaba's Qwen 3.6 27B on agentic code review tasks, finishing faster due to superior Multi-Token Prediction (MTP) design, according to benchmarks and field reports. While Qwen 3.6 leads …