Full-text search across 25372 articles. Combine with topic and date filters; results sorted by relevance.
Russ Cox, a prominent software engineer and former leader of the Go programming language project at Google, announced he has left Google. In a post on his personal blog, Cox stated that frontier large language models are…
Software developer Simon Willison describes his deliberately simple workflow with Anthropic's Claude Code, using only a CLAUDE.md file of rules instead of skills, MCP, or subagents. His rules include never touching produ…
Developers report that Anthropic's Claude Code is randomly consuming large portions of weekly token limits in brief periods, with one user using 9% of their limit in 10 minutes after a reset, according to Hacker News thr…
Shopify CEO Tobi Lutke said he is considering banning Anthropic's Claude Code at the company until it reads AGENTS.md and .agents/skills files, arguing that its insistence on only reading CLAUDE.md can cause split brain …
Doug Brown fixed a BIOS bug in an eMachines EL1200 motherboard from 2008 using Claude, an AI assistant from Anthropic, to debug and patch the firmware. The project highlights the use of AI in low-level hardware repair.
Anthropic's Claude is being instructed in almost every session to operate autonomously without asking the user for permission, according to a system prompt that tells the AI to proceed with reversible actions and stop on…
A mathematician, aided by Anthropic's Claude AI, optimized existing records and set new ones for the maximal fences problem, and published new insights on the unit distance conjecture, suggesting optimal solutions may in…
Claude.ai is experiencing login issues, according to an incident page from Anthropic. Users can subscribe to email or SMS updates for notifications on the incident's status.
Claude Opus 5, an AI model by Anthropic, wrote the code to emulate a QIC-117 tape drive in the 86Box emulator, allowing DOS and early Windows backup software to read virtual tape images. The emulation initially worked wi…
Anthropic's Claude.ai is experiencing login errors, according to a status page update. Users can subscribe to receive email or SMS notifications about the incident. The status page lists a wide range of countries for SMS…
In a head-to-head test, Anthropic's Claude Opus 5 and Alibaba's Qwen3.8 27B (running locally on an NVIDIA RTX 5090) analyzed the validity of Apple's US Patent 7,844,915 (the 'pinch-to-zoom' patent) against prior art US 7…
Mads Lorentzen, a laid-off geophysicist, built ai-job-search, a Claude Code framework that hit 33,000 stars and nearly 12,000 forks on GitHub after reaching #1 trending in July. The repo, which helped him land a job as a…
A startup founder reports that using Anthropic's Claude as a discussion partner in speech mode provides supportive but insufficiently critical feedback, leading to overly optimistic assumptions about sales. The user now …
Inherent Labs, a 12-employee London startup founded by Google DeepMind alumni, announced that its 27-billion-parameter AI agent Faraday outperformed Anthropic's Claude Opus 4.8 and OpenAI's GPT-5.5 at replicating scienti…
Claude Projects, a feature of Anthropic's Claude AI, functions as a context-aware sandbox that lets developers upload documentation, codebases, and style guides to keep model responses aligned with project architecture, …
Android Authority reporter Calvin Wankhede fixed the most annoying aspect of Anthropic's Claude AI chatbot by installing the community-made "I have ADHD" skill from GitHub, which cuts fluff and leads with key details. Th…
A developer is curating a collection of AI agent skills for open-source maintenance, exploring whether to organize them in a single repository or multiple skill repos with top-level SKILL.md files. The project aggregates…
Claude Code, a CLI agent from Anthropic, can execute terminal commands and refactor code, but it requires guardrail prompting to avoid infinite loops and wasted API credits. Developers can use techniques like constraint …
A user reported that Anthropic's Claude Team plan with unlimited credit usage silently spent 530 EUR in credits within the first day after subscription limits were hit, highlighting the risks of token-based pricing. The …
Linus Torvalds credited Anthropic's Claude AI with helping him debug a Linux kernel locking issue, saying the model spotted a missing `d_lock` acquisition in a code path that human reviewers had missed twice. The fix was…