May 25 · 5 min read · Something happened in web development in the past 18 months, and I don’t think we’ve really processed it as a community yet. It's not just that AI tools got better. It's that the nature of the job sta
Join discussion
May 19 · 5 min read · There's a pattern I've noticed in developer communities over the past year. Every few months a new AI coding tool launches, gets a wave of "these changes everything" posts, and then, if you check back
Join discussion
May 12 · 5 min read · Originally published at devtoolpicks.com Anthropic just shipped Claude Code v2.1.139. Two features in one release: agent view, which gives you a single dashboard for all your Claude Code sessions, and the /goal command, which lets Claude work auton...
Join discussion
May 11 · 5 min read · Originally published at devtoolpicks.com Anthropic just made the Claude Platform on AWS generally available. The announcement came from the official @claudeai account today, and Hetzner immediately jumped into the replies, which tells you something...
Join discussion
May 11 · 7 min read · Originally published at devtoolpicks.com Most CLAUDE.md files are written once, during initial setup, then forgotten. They contain three lines about the tech stack and a reminder to write tests. Claude ignores half of it because nothing is specific...
Join discussion
May 6 · 8 min read · Originally published at devtoolpicks.com Your AI coding agent can now create a Cloudflare account, register a domain, start a paid subscription, and deploy a live application. All from one CLI session. No dashboard. No copy-pasting API keys. No man...
SSweepBase commented
May 6 · 6 min read · Originally published at devtoolpicks.com Anthropic just announced three changes to Claude Code, all effective immediately. First, Claude Code's five-hour rate limits are doubled for Pro, Max, Team, and seat-based Enterprise plans. Second, peak hour...
Join discussion
May 5 · 8 min read · Originally published at devtoolpicks.com When Claude Opus 4.7 launched on April 16, Anthropic positioned it as their most capable generally available model. SWE-bench numbers improved. Agentic persistence got better. The marketing was clean. Three ...
Join discussion
