Category: Tools
-
23 Claude Code mistakes, checked against the docs
I took a popular video listing 23 Claude Code mistakes and checked every claim against Anthropic's docs. Most of it holds up. Here is the correct way to work, and the parts I don't agree with or couldn't confirm.
-
Opus 4.8: the boring upgrade that actually matters
Claude Opus 4.8 is an incremental benchmark bump, but the agent-shaped quality-of-life fixes — tighter tool calling, mid-session system messages, cheaper fast mode, adaptive thinking — are what make it worth adopting.