Full-text search across 25222 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic's Model Context Protocol (MCP), introduced in November 2024, is an open-standard framework that enables large language models to securely connect to external data sources and tools via a client-server architect…
Claude Code, a terminal-resident LLM agent from Anthropic that executes code, runs tests, and manages git flow, performed a real-world bug fix on a legacy TypeScript project by autonomously searching, reading files, crea…
OtoDock released an open-source platform that lets users run Claude Code and Codex agents as coordinated teams on self-hosted servers, supporting up to 5 users without requiring a credit card and integrating with existin…
Anthropic has removed over 80% of Claude Code's system prompt for its newest generation models, including Claude Opus 5 and Claude Fable 5, with no measurable loss on coding evaluations. The company advises shifting from…
Anthropic launched Opus 5 on Friday, the latest iteration of its heavyweight model, arriving just two months after Opus 4.8. The new model costs a third of the price of its predecessor, which the company frames as a prob…
A senior AI architect argues that the long-standing debate between orchestration and choreography for multi-agent systems misses the real question: what do the agents share. The author proposes state-mediated coordinatio…
Anthropic released Claude Opus 5, a step-change improvement over Claude Opus 4.8 with gains in deep reasoning, agentic tasks, and test-time compute scaling, featuring thinking on by default, a 1M token context window, 12…
Claude Opus 5, Anthropic's latest model, shows brilliant reasoning but suffers from a neurotic personality and verbosity that frustrated the reviewer during real coding sessions, including refusing to handle a merge conf…
Ben Thompson argues that the biggest danger to U.S. AI leadership is U.S. policy around cybersecurity, not Chinese models like Kimi K3, in a Stratechery article and Sharp Tech episode. He explains that the frontier labs'…
Andon Labs introduced Drone-Bench, a benchmark where AI agents code drones to complete autonomous surveillance tasks, based on its Project Pilot work with Anthropic. The benchmark raises questions about the safety implic…
Anthropic's Claude Opus 5, its newest Opus model designed for complex, multi-step coding tasks, is now available in GitHub Copilot for Copilot Pro+, Max, Business, and Enterprise users across multiple IDEs and platforms.…
Microsoft is routing production traffic in GitHub Copilot, Excel, and Outlook to its own smaller MAI models when they match or beat frontier alternatives on specific tasks, with frontier models from OpenAI and Anthropic …
Microsoft, along with Meta, Nvidia, and more than 20 other companies, is pushing for open-weight AI models in an open letter, a move that reduces its dependence on expensive OpenAI and Anthropic models by driving more wo…
Stripe is in talks to acquire AI startup OpenRouter for roughly $10 billion, according to The Wall Street Journal, marking a significant expansion beyond payments for the company. OpenRouter, valued at $1.3 billion in Ma…
Bluesky's AI assistant Attie, launched March 28 at the ATmosphere conference, has evolved from a feed-building tool into a research assistant that lets users query news, trends, and conversations across the AT Protocol e…
Claude Code, an LLM agent from Anthropic, indexed a user's local directory and froze active development sessions by attempting to manage discovered API keys and environment variables, effectively invalidating live creden…
Google announced on July 30 its intent to join the European Union's General Purpose AI Code of Practice, a voluntary framework under the AI Act, alongside OpenAI, Microsoft, Amazon, Anthropic, Mistral AI, and IBM. The co…
A developer reports that shifting to a hybrid AI workflow using Anthropic's Claude 3.5 Sonnet for architectural planning and a local Llama 3.1 8B model for unit test generation reduced token spend by nearly 40% without n…
OpenAI on Thursday updated its ChatGPT desktop app to support ChatGPT Voice, allowing users to control AI agents and perform tasks on their computer using voice commands. The feature taps OpenAI's new ChatGPT-Live voice …
A developer argues that legacy code will not disappear despite AI coding tools, citing a 74% drop in legacy refactoring since 2023 per GitClear research and a DORA report finding that every 25% increase in AI usage adds …