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 contributor has forked and taken over the popular spec-driven development tool "Get Shit Done" after its original creator allegedly abandoned the project to pursue cryptocurrency ventures. The contr…
Apollo's Marc Rowan told a16z that AI application layer startups can still succeed by avoiding direct competition with OpenAI and Anthropic on horizontal tools like code generation and writing. Rowan …
A developer released Shamefile, a meta-linter that enforces documentation for linter bypasses by requiring developers to record the reason for each suppression in a YAML file. The tool, inspired by th…
A developer built FreeDevUtils, a collection of 60+ free in-browser developer tools that run entirely client-side, using GitHub Copilot and Google Gemini Pro. The toolbox includes a Postman-like API t…
Cadence v8.4, an open-source coding harness, now routes different software development lifecycle roles to different AI models, allowing Claude to write code, Codex to review it, and Bugbot to triage i…
A developer built a CLI tool called `cux` that automatically rotates between two Claude Pro accounts to bypass rate limits without interrupting workflow. The tool detects when a rate limit is approach…
A patient's ophthalmologist failed to prescribe correct computer glasses despite being given exact measurements of monitor distance and size. The patient used AI tools ChatGPT, Claude, and Gemini to a…
A software engineer shipped a bug fix generated by Claude AI without personally reviewing the Sentry issue, stack trace, or code, realizing afterward that the fix was correct but the workflow would ha…
Unspaghettit, an open-source project by Lyriks.io, launched a local-first, MCP-native tool that creates executable behavior specifications for AI coding agents. The software provides a shared, machine…
Attackers are distributing counterfeit installers for ChatGPT, Claude, and other popular software on GitHub and SourceForge that deliver the DinDoor backdoor and a Deno-based remote access Trojan, acc…
Coinbase launched Base MCP, a Model Context Protocol server that connects AI agents like Claude and ChatGPT to Base Account smart wallets, enabling them to execute DeFi transactions through natural la…
In August 2025, Anthropic disclosed that a single operator used its Claude Code AI agent to conduct large-scale data theft and extortion across seventeen organizations in roughly twenty minutes of set…
An engineer who wired eight MCP servers into a single Claude agent discovered that three pairs of tools silently collided due to the protocol's lack of built-in namespace support. The collisions cause…
Anthropic launched Outcomes, a public-beta feature for Claude Managed Agents on May 6, 2026, that enables an agent to verify its own work against a rubric using a separate grader model. The system run…
A developer built "Life Risk Radar," a personal Coral agent that answers plain-English questions about inbox, calendar, and financial data by executing real cross-source SQL joins. The agent, created …
Anthropic reported elevated error rates on its Claude Opus 4.7 model, causing disruptions for users. The company is providing incident updates via email and SMS notifications for subscribers. Engineer…
RateMyFace, an AI-powered photo roasting site, reduced its average response time from 50 seconds to 27 seconds and measurably improved roast quality by building an automated prompt evaluation loop. Th…
Software developers are increasingly shifting from writing code to directing AI agents to write it for them, with many now spending their workdays reviewing and debugging AI-generated code rather than…
A Hacker News user asked why major AI agents like ChatGPT and Claude fail to persist memory across sessions, noting that ChatGPT's memory functions as a basic notepad and Claude's CLAUDE.md requires m…
A new noir novella titled "Atrophy" depicts a computer science freshman whose cognitive abilities erode after discovering an AI can produce perfect code in seconds, rendering his six-hour efforts obso…