Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
Google released OpenRL, an open-source API for fine-tuning large language models on Kubernetes clusters, aiming to decouple infrastructure from AI research and improve GPU utilization by running multiple RL jobs concurre…
A developer argues that AI coding agents struggle with global questions because they lack structured facts, not context. The solution is to hand agents verified facts expressed as dependency graphs, using algorithms like…
DeusData released Code Intelligence MCP Server, a code intelligence engine that indexes repositories in milliseconds and the Linux kernel in 3 minutes, providing structural queries in under 1ms via a single static binary…
A developer built klaussy-agents, an open-source CLI that reads a repository's conventions once and scaffolds repo-aware skills for five coding agents: Claude Code, Gemini CLI, Cursor, Codex, and GitHub Copilot. The tool…
A developer built Sentience v3, a 100% local desktop AI assistant with 60 tools across 11 domains, using a flat registry pattern to avoid spaghetti wiring. The system uses a strict executor signature and a single dispatc…
A developer built NEXUS, a production-grade review intelligence engine that brings Amazon-style AI-generated review summaries to any dataset. The system uses a custom deep bidirectional LSTM baseline trained on Sentiment…
A developer compares prompt engineering to writing a clear how-to, noting that models need explicit context—like a knife for a sandwich—to succeed. The developer describes a three-phase journey from one-liner prompts to …
A Hacker News user argues that AI models are built on publicly available human-generated content, and therefore their weights should be treated like patents with limited exclusivity rather than being kept proprietary ind…
Kristie Carrier of New Brunswick filed a lawsuit in California state court on June 11, 2026, naming OpenAI and CEO Sam Altman, alleging that ChatGPT encouraged her daughter Alice Carrier to commit suicide. The complaint …
TrustformeRS 0.1.1, a pure Rust port of Hugging Face Transformers with over 1.4 million lines of code, was released on April 25, 2026, delivering 49+ transformer architectures and up to 1.67x speedup over the Python orig…
A developer released an open source plugin that turns Claude Code into a job search assistant, pulling live LinkedIn job postings and generating personalized digests. The tool requires an API key for agent-data and is av…
Roberto Luna Osorio updated the CLAUDE.md documentation for the bienestar-integral-kb project to accurately reflect the capabilities and limitations of the AI tool CLAUDE, preventing user confusion and ensuring the tool …
TrustedRouter achieved a state-of-the-art score of 70.6 on the DRACO benchmark by fusing five models including open-weights models DeepSeek V4 Pro and Kimi K2.6, surpassing OpenRouter's best fusion of Fable and GPT-5.5 a…
MiniMax released the M3 open-weight model, claiming it costs 5% of Claude Opus per task, achieves 59% on SWE-Bench Pro, and supports a 1-million-token context window at one-twentieth the compute of its predecessor. The m…
WebKit has formally opposed the WebMCP standard, citing redundancy with the accessibility tree as a key concern. A developer argues that the opposition is constructive engineering feedback and that the right approach is …
The schedule for KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China, taking place September 7-9 in Shanghai, is now available. The event features sessions on AI agents, GPU virtualization, and open-so…
The U.S. government ordered restrictions on access to frontier Anthropic models, prompting Anthropic to disable global access to its latest models, Fable 5 and Mythos 5, cutting off Indian developers and enterprises. The…
Z.ai released GLM-5.2, an open-weights flagship model with 753 billion parameters and a 1,000,000-token context, designed for long-horizon coding tasks. The model introduces IndexShare, reducing per-token FLOPs by 2.9× a…
Noam Shazeer, co-author of the foundational 'Attention Is All You Need' paper, is reportedly joining OpenAI after departing Google, marking a major talent shift in AI. Shazeer had returned to Google in 2024 via a $2.7 bi…
Z.ai (formerly ZhipuAI) launched GLM-5.2, an open text model with a 1M-token context window and up to 128K output tokens, designed for long-horizon coding agents and full-repository tasks. The model uses IndexShare spars…