Claude is a family of AI assistants developed by Anthropic. Named versions (Claude 3.5 Sonnet, Claude 3 Opus) are known for long context windows, coding ability, and safety-focused design.
A reproducible benchmark of 24 local, self-hosted, and cloud LLMs for translation into English found that a local 18 GB model (gemma-4-12b-qat) performs on par with frontier cloud models on Afrikaans→…
A 16-year-old developer built FolioDux, an open-source file-mapping standard that reduces token usage in AI-assisted development by providing a compact index of a project's structure. Instead of feedi…
Most companies integrate AI into development by giving developers AI assistants without changing their process, leading to review bottlenecks. The author proposes shifting engineering work to spec-dri…
Perplexity released a new memory system called Brain that will serve as a shared connective layer across its core products, including Perplexity Search, the Perplexity Computer agent, and the Comet br…
Anthropic launched enterprise-managed authorization for MCP connectors through Okta, allowing administrators to centrally provision connector access across Claude chat, Claude Code, and Cowork. The fe…
SkillsGuard, a static security scanner for AI agent skill packages, has been released as an open-source tool that detects malicious SKILL.md files and bundled scripts before execution. The scanner dec…
A developer built Proximo, an open-source Proxmox MCP + A2A server that requires user approval before executing destructive actions and maintains an audit trail. The tool, developed with assistance fr…
A developer using Claude's MCP and conversation memory features reports a significant reduction in the effort required to re-explain context, leading to faster and deeper conversations. By connecting …
Vlad Podoliako released a free, public book titled 'Vlad's Playbook: The Ultimate AI Dive Deep' with 47 chapters on operating AI coding tools, available on GitHub without signup. The book covers pract…
Researchers at the University of Montreal argue that fluent, emotionally responsive behavior in AI chatbots stems from statistical computation, not subjective awareness, drawing an analogy to the neur…
A high-school student built a free app called Revise to combat summer learning loss. The app generates exercises, reading texts, and flashcards on a spaced-repetition schedule for subjects like math, …
Airgap, a new Linux tool, wraps programs in namespaces to hide secrets from AI agents and block npm malware that steals credentials at install time. It redacts sensitive files like .env and SSH keys f…
1min.AI, an AI platform integrating ChatGPT, Claude, and Gemini, is available for a one-time payment of $69.97, down from a $540 value. The deal offers a lifetime subscription to the advanced business…
Rising AI compute costs are driving enterprises to adopt cheaper Chinese models like DeepSeek, with U.S. developers reporting costs of $10 per hour on Claude versus under $0.50 on DeepSeek. Companies …
John Jumper, the Google DeepMind vice president and Nobel Prize-winning scientist behind AlphaFold, is leaving the company to join Anthropic, the maker of the Claude AI assistant. His departure signal…
An open-source space MMO lets players mine, trade, fight pirates, and jump across the galaxy in a browser, built with Claude and unaffiliated with CIG/RSI.…
Shrijith Venkatramana, building git-lrc, explains the three phases of post-training that transform pretrained LLMs into helpful assistants. The process starts with supervised fine-tuning (SFT) on cura…
A Hacker News user asked how to prevent coding agents from generating poor UI/UX designs, with commenters suggesting providing reference screenshots or design inspirations and explicitly instructing t…
Developer Alex Reysa released glueRun-go, an open-source orchestration engine that runs autonomous AI coding agents in parallel against software repositories using a three-tier scheduling model with g…
The Model Context Protocol's Enterprise-Managed Authorization extension, stable since June 18, 2026, redefines authorization as a context-scoping mechanism that determines which data sources an AI age…