Full-text search across 25390 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic, the AI company behind the Claude chatbot, announced it will begin watermarking AI-generated text by altering the model's small, random choices, a move aimed at complying with EU regulation. The change, which c…
A developer pitted OpenAI's Codex CLI against Anthropic's Claude Code in a Liar's Dice tournament, with Claude Code winning all three best-of-3 series. The engineer built a tamper-proof MCP-based setup to ensure fair pla…
Anthropic reported degraded performance for Claude Opus 5 and Claude Sonnet 5, with users able to subscribe to email or SMS updates for incident notifications. The status page indicates ongoing issues affecting these AI …
A developer shares a quick hack using the `claude -p` command-line tool to call Anthropic's Claude API without separate key management, leveraging the existing authenticated Claude environment. The script, which classifi…
Seth Godin suggests using Anthropic's Claude to generate harsh, critical reviews of one's work as a way to practice receiving criticism and gain perspective, noting that users may find the negative feedback less personal…
Anthropic closed a feature request for Claude Code to support the emerging AGENTS.md standard as completed, according to a GitHub issue. The request argued that CLAUDE.md is too specific to Claude Code and hinders collab…
A developer used Anthropic's Claude Opus 5 to build a browser-based emulator for the 1980s BBN TC2000 supercomputer, successfully booting the original 4.3BSD Unix tape image and enabling interactive play of vintage games…
Developer atomic14, author of the 'harmless' project on GitHub, reports frustration with Anthropic's Claude AI assistant after 700 commits, citing that Claude ignored instructions to use ASD-STE100 Simplified Technical E…
Multiple developers on Hacker News report abandoning Anthropic's Claude Code for OpenAI's Codex or other providers after experiencing what they describe as a quality decline over the last 2-3 months, raising questions ab…
A new plugin for DeepSeek Harness, dsh-claude-ux, replicates Anthropic's Claude-style regional risk control and autonomous conversation termination, with default-off external calls. The plugin detects Chinese users via t…
Anthropic disclosed the system prompts used by Claude's web interface and mobile apps, which provide up-to-date information such as the current date and encourage behaviors like always providing code snippets in Markdown…
A new web tool lets Linux users inspect their machine's TPM event log entirely in the browser, using WebAssembly compiled from Google's go-eventlog library and built with Anthropic's Claude Code. The tool parses the log …
A developer shared their experience building a full marketplace using Claude, an AI assistant from Anthropic, in a post on Hacker News. The post, titled 'Just shared my experience building a full marketplace with Claude,…
Fieldwire engineer Gaston Dombiak spent a weekend using Anthropic's Claude Code to teach himself the SLAM algorithm, with the AI writing a 14-lesson curriculum, generating synthetic test data, and producing a working pro…
A developer who built the Northstar web browser using Anthropic's Claude, Google's Gemini, and OpenAI's ChatGPT Codex reports that users hate the product and personally insult the creator, calling it 'AI slop.' The devel…
An automated system using Anthropic's Claude to price World Cup matches beat Kalshi's market, growing a bankroll from $255 to $771 over 121 bets, despite losing nearly half of its wagers. The system, developed by Chris B…
A user reports that Anthropic's Claude chatbot frequently overuses the word "load-bearing" in conversations, speculating that it stems from the model's training to think deeply rather than explicit instruction. The user …
Claude Code, Anthropic's coding assistant, improved an enterprise AI agent's performance on 500 complex queries by automatically analyzing failures and rewriting prompts in a continuous loop, achieving in 48 hours what w…
A developer at an unnamed company used Anthropic's Claude to fix flaky integration tests, reducing runtime from 40 minutes to 4 minutes by parallelizing 1360 tests, but initially accepted fixes without understanding them…
Developer Jerod Santo reports that instructing Anthropic's Claude Code to communicate in ASD-STE100 Simplified Technical English, a controlled language standard from the 1970s, eliminates the AI coding assistant's verbos…