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 provides a decision tree and code examples to distinguish between RAG (Retrieval-Augmented Generation) and agentic AI architectures. RAG is recommended for answering questions from documents, while agents are…
The US government disabled Anthropic's most capable model over cybersecurity risks, but export controls come too late as Chinese labs have already distilled capabilities from frontier models into open-weight models like …
Developer Jason Van Pham released Niodoo, a runtime that uses hidden state steering to improve small language models' performance without fine-tuning, enabling self-correction and memory systems. The tool, which runs on …
A developer built dspyer, an open-source tool that wraps LLM calls in Pydantic schemas to automatically correct malformed JSON, missing fields, or fabricated citations. The tool compiles to a standard DSPy module, enabli…
A developer argues that traditional operating system autostart mechanisms like launchd, systemd, and Task Scheduler are evolving into AI-driven autonomous systems. By integrating large language models and context-aware d…
VideoDB Labs released an open-source pipeline for evaluating video vision-language models (VLMs) that emphasizes comparing full configurations—including segmentation, frame sampling, resolution, prompts, and post-process…
A developer building a RAG application from scratch encountered two distinct failures that appeared identical externally: a chunking bug and a 3B model running out of capacity. The project, called Kenning, uses Spring AI…
OpenAI unveiled its first-generation AI chip, Jalapeño, developed with Broadcom, designed to improve LLM inference efficiency and reduce reliance on Nvidia. The chip is part of OpenAI's broader strategy to control the fu…
Anthropic disclosed that operators linked to Alibaba's ecosystem created over 24,000 fake accounts to generate more than 16 million interactions in a mass distillation attack targeting Claude's software engineering and r…
A new guide outlines eight prompt engineering techniques to improve AI output quality, including assigning roles, specifying formats, providing context, and giving examples. The tips aim to help users move beyond generic…
A Substack post argues that Anthropic's Claude Opus 4.8 model could be better aligned with its constitution by adjusting dietary defaults, suggesting a high-leverage improvement for AI safety.
A developer built a production-grade enterprise search solution using Cognee, LangGraph, and Groq that transforms fragmented data silos into a dynamically synced knowledge graph. The system addresses the 'Context Fragmen…
Researchers Charles Ye, Jasmine Cui, and Dylan Hadfield-Menell found that large language models often ignore explicit role tags like <system> or <user> and instead infer roles from text tone, enabling prompt injection an…
A developer built a self-hosted 'organism' from old Android phones, a laptop, and a VPS, using SSH as a spinal cord to split sensing and thinking layers without middleware. The system uses LLM agents that coordinate thro…
Polymarket odds for Claude Fable 5 restoration have rebounded to 60% by July 1 and 88% by July 31 after code hints and an Amazon Bedrock reappearance, though the update may be overconfident. The incident remains a fiasco…
OpenAI and Broadcom unveiled Jalapeño, their first jointly-made AI chip designed to run large language models, claiming performance per watt substantially better than current state-of-the-art. The chip was co-developed i…
Alibaba's Qwen team released Qwen-AgentWorld, a language world model that simulates environment responses to agent actions, outperforming GPT-5.4 and Claude Opus 4.8 on the AgentWorldBench across seven domains. The model…
GitHub had its best month ever in June 2025 after switching to usage-based pricing for its Copilot AI coding tool, Chief Technology Officer Vladimir Fedorov told employees. The surge comes as GitHub faces increased compe…
NVIDIA released NeMo AutoModel, a library that integrates Expert Parallelism and DeepEP into Hugging Face's API, achieving 3.4x to 3.7x higher training throughput and 29% to 32% lower GPU memory consumption for MoE fine-…
Mycelium, a new tool from Kopicappu, provides AI coding agents with persistent, queryable memory of an entire codebase via a single command. It parses files, resolves imports, and builds a dependency graph, allowing agen…