📰 Dev.to · gentic news

YC CEO Garry Tan open-sourced gstack, a pack of slash commands that turns Claude Code into a structured team of specialists, claiming it helps ship 10

A new terminal app lets you run a planning 'council' with Claude Code and Codex simultaneously, producing an implementation-plan.md to kickstart your

Researchers introduce ReCUBE, a benchmark isolating LLMs' ability to use repository-wide context for code generation. GPT-5 achieves just a 37.57% str

A deep dive into Cursor's scattered 8GB local storage reveals why Claude Code's ~/.claude/projects/*.jsonl approach is better for developers.

Airut is an open-source system that lets you trigger and manage Claude Code tasks via email/Slack threads, with full container isolation and credentia

Use the official Notion MCP server to log your AI script's output directly to a Notion database, creating a real-time dashboard without writing API ca

A comprehensive arXiv review categorizes five principal KV cache optimization techniques—eviction, compression, hybrid memory, novel attention, and co

AI is transforming demand forecasting, shifting roles from manual data processing to strategic analysis. The article identifies five key positions bei

Claude Code's deny lists only check the first token of compound commands, allowing dangerous actions like 'git clean' to slip through. Here's how to p

A developer used Claude Code to create a structured JSON-to-PDF knowledge base with 105 quotes, demonstrating how to build RAG-ready datasets faster t

Google released TurboQuant, a novel two-stage quantization algorithm that compresses the KV cache in long-context LLMs. It reduces memory by 6x, achie

Researchers demonstrate that large language models can effectively deanonymize online users by analyzing their writing style and content across platfo

A controlled study of 51 post-training algorithms across 240 runs finds algorithm performance rankings completely invert between 1.5B and 7B parameter

Alibaba researchers propose AIGQ, a hybrid generative framework for pre-search query recommendations. It uses list-level fine-tuning, a novel policy o