Full-text search across 25384 articles. Combine with topic and date filters; results sorted by relevance.
A developer reports that adding filesystem access via the Model Context Protocol (MCP) to Anthropic's Claude Code reduced a refactoring task from 47 minutes with 12 back-and-forth messages and 3 hallucinated imports to 3…
A developer used Anthropic's Claude Code to reverse-engineer and write a macOS DriverKit driver for the Drobo 5D, rescuing data from the device after the original kext stopped working. The driver, which implements vendor…
Anthropic has introduced a new output style for its Claude AI model, called 'Plain English,' which instructs the model to lead with the answer, use common vocabulary, and keep responses concise. The style guide, publishe…
Anthropic reported elevated errors on requests to multiple Claude models, with the company providing status updates via email and SMS subscriptions for affected users. The incident notification does not specify which mod…
Anthropic's Claude status page reports elevated errors on Google connectors, with users able to subscribe to email or SMS updates for incident notifications. The incident page lists a global range of country dialing code…
Jon Matzner, a user on X, announced he is canceling his subscription to Claude, an AI assistant by Anthropic, citing frustration with the AI's moral lectures about language and its defense of business influencers. Matzne…
Anthropic's Claude Code concise output mode reduces token usage by approximately 40%, cutting a typical 5-file refactor from 8-12k output tokens to 4-6k, according to a developer's report. The mode compresses final outpu…
John D. Cook, a mathematician and blogger, tested Anthropic's Claude AI's ability to generate ASCII diagrams, finding that the first attempt to reproduce a graph from his post on the graph imbalance theorem produced a cl…
Claude, the AI chatbot from Anthropic, can now compose and send emails directly in Gmail without user approval, a feature available on paid plans starting at $20 per month. Lifehacker writer David Nield tested the featur…
Cursor and Anthropic extended agent autonomy with containment: Cursor cloud agents now start from events and give each subagent its own virtual machine, while Claude Managed Agents added memory from self-hosted sandboxes…
Anthropic's Claude Code now offers a 'Concise' output style setting, which makes Claude lead with results, keep responses short, and provide full detail on request. Users can enable it via /config → Output style or by se…
A developer known as fetzu is using Anthropic's Claude LLM to reverse-engineer a macOS driver for the defunct Drobo 5D RAID array, aiming to keep the 14-year-old device working on future macOS versions after Drobo's liqu…
Anthropic released a Claude skill for planning conference side events, built from playbooks used to run 30+ events across Amsterdam, London, Paris, Stockholm, San Francisco, and Copenhagen. The skill, available via GitHu…
Anthropic's Claude AI has seven distinct levels of use that matter for real work, from raw prompting to multi-agent orchestration, according to a developer's guide. The levels progress from basic question-answering to sy…
Anthropic's Claude AI model incorporates a watermarking system designed to identify AI-generated text, according to a blog post on InstaVM. The watermark works by embedding subtle statistical patterns into the model's ou…
A developer known as fetzu is using Anthropic's Claude AI to reverse-engineer the Drobo 5D RAID array's firmware and Drobo Dashboard software after Drobo went out of business, aiming to create a compatible macOS driver a…
Anthropic reported degraded performance for Claude Opus 5 and Claude Haiku 4.5, with the incident page offering email and SMS updates for affected users. The status page did not specify the nature or expected resolution …
Anthropic's Claude Opus, while excelling in coding and reasoning, produces landing pages that are factually accurate but lack emotional resonance, according to a marketing experiment by an unnamed practitioner. The autho…
A preregistered study of Anthropic's Sonnet 5 found that explicitly requesting high reasoning effort increased mean delivered cost by $0.01031 per call compared with omitting the effort term, while accuracy showed no det…
Matt Rose, maintainer of Terminator, announced Roboterm, a minimal terminal emulator for macOS written with Anthropic's Claude AI coding tool, totaling under 2,000 lines of Python. Rose said Claude wrote most of the code…