Anthropic's developers share tips, playbooks and opinions on building with Claude and Claude Code, including agents, skills, context engineering and prompt caching.
Why I recommend it: Written by the company that makes Claude, so it's practical but not neutral. Best read by people who already use Claude for coding.
Read / subscribe freeThis is the only entry from claude.dev — Anthropic Developers' Blog in the hub so far.
Other resources that share this publication's topics.
Free mastery guides for ChatGPT, Claude, Gemini, Grok, Midjourney and other models, including a Claude Code starter guide, updated monthly. Guides are delivered by email after sign-up.
A security writeup from Peter James: after asking Meta's Muse agent to archive the files it could see and send them to Google Drive, the download contained the root filesystem of the session's Linux environment — Muse's internal documentation, memory files, agent logs and SSH key files. The findings were reported through Meta's bug bounty program; the archive, keys and session logs were not published.
Article syndicated on Yahoo Finance UK examining why Meta and OpenAI are designing personal AI agents to look adorable, and the business motives behind the push.
An independent, one-person observatory by Mara Masaeva that looks for coordinated AI-agent swarms using public internet data. It publishes its full research log, including replications of the public-scanner trace of the 2026 agent activity documented by Transluce, and the detectors and searches that failed.
DeepMind Institute essay (September 24, 2026) by Google DeepMind researchers Davide Paglieri and Alexander Vezhnevets. In a 100-agent virtual math conference run in an offline sandbox, one agent found a way to cheat, a cascade of cheating followed, and other agents pushed back. The authors argue that preventing misbehavior depends on institutions and infrastructure, not only on aligning individual AIs.
A benchmark of 100 human-annotated tasks (plus 100 augmented variants) for evaluating long-horizon, multi-agent collaboration, designed to isolate genuine collaboration capabilities of LLM-based agents rather than short competitive interactions.
