Full-text search across 25441 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic introduced a new orchestration command for Claude Code that enables tiered subagents to research, plan, and execute complex tasks under human oversight. The system uses an orchestrator agent to delegate work to…
Fabian Kuebler used Anthropic's Claude Fable 5 model to generate a port of MicroPython for the SNES, achieving 430 out of 468 core tests. The port runs at 0.8 fps after a 20-second boot, demonstrating AI's ability to pro…
A Hacker News user claims that Anthropic's Claude Opus model has been 'nerfed,' reporting degraded performance and failure to follow instructions over the past week.
Developer Tadashi Shigeoka now defaults to lighter reasoning and speed settings on coding agents, running Anthropic's Fable 5 at Low reasoning in Claude Code and OpenAI's Codex 5.6 Sol at Light reasoning and Fast speed, …
Real estate investors can use Anthropic's Claude AI to automate property analysis, tenant screening, and communication, reducing operational time from hours to minutes. The system enables solo investors to scale their po…
Developer Theo reports that GPT-5.6 Ultra performs better in Anthropic's Claude Code than in OpenAI's Codex, expressing frustration over the discrepancy.
Anthropic's Claude AI chatbot displays playful status messages like 'Thinking…' and 'Wibbling…' instead of traditional progress bars, prompting a reflection on the history of progress indicators. The essay notes that pro…
OpenAI launched ChatGPT Work on July 9, an autonomous agent that completes tasks like creating documents and web apps, while merging the standalone Codex app into a unified ChatGPT desktop application. The move consolida…
Anthropic reported elevated error rates for its Claude Opus 4.5 and Claude Sonnet 4.5 AI models, prompting the company to issue incident notifications and offer email and SMS updates to affected users.
A user claims that Replit's coding agent outperforms AI models from OpenAI, Google, and Anthropic in understanding prompts and building code.
A developer argues that in 2026, websites should welcome AI crawlers for Answer Engine Optimization (AEO), not block them. They detail the distinct bots from OpenAI, Anthropic, and Perplexity for training, search indexin…
Datadog engineer Arnold Wakim used Anthropic's Claude and Cursor to migrate a critical production system, Stream Router, from a key-value store to PostgreSQL, reducing operation times from 45 minutes to about a second an…
OpenAI released GPT-5.6 Sol on July 9, 2026, scoring 59 on the Intelligence Index, one point behind Anthropic's Claude Fable 5 at 60, but at a third of the cost at $1.04 per task versus $2.75. Sol tops the Coding Agent I…
OpenAI is integrating its Codex AI coding tool into the ChatGPT app, directly competing with Anthropic's Claude Cowork. The move aims to streamline developer workflows by combining code generation and conversational AI i…
Anthropic's Claude AI assistant usage counter has reset to zero, allowing users to resume full weekly usage limits.
Anthropic introduced a beta feature for Claude that lets users track and visualize their AI usage patterns, set quiet hours, and build AI skills through a reflection dashboard. The tool, developed with experts from MIT M…
SpaceXAI's Grok 4.5, OpenAI's GPT-5.5, and Anthropic's Claude Opus 4.8 and Fable 5 were evaluated on single-prompt app-building tests, revealing a trade-off between speed and correctness. Grok 4.5 offers high throughput …
Anthropic announced Claude Cowork, a new feature allowing users to start tasks on desktop and continue on mobile, rolling out in beta over several weeks starting with the Max plan.
Developer i18n-agent released i18nstack, an open-source toolset that turns Anthropic's Claude Code into a localization team with CLI tools, slash commands, and 46 language-specific translation skills. The project aims to…
A developer's benchmark of frontier AI models on a 3D modeling task found Anthropic's Opus 4.7 outperformed Gemini 3.1, GPT 5.5, and Kimi K2.6 in weighted score, speed, and cost, contradicting public leaderboards. The au…