Claude Sonnet 5 Review: A Week With Anthropic's New Default
Claude Sonnet 5 review after a week: it nearly matches Opus 4.8 on coding, beats it on Terminal-Bench, and runs at just $2/$10 — but the tokenizer bites.
Claude Sonnet 5 review after a week: it nearly matches Opus 4.8 on coding, beats it on Terminal-Bench, and runs at just $2/$10 — but the tokenizer bites.
Learn to build 4 real Claude Code workflow scripts for code audit, migration, security review, and research. Includes actual output and cost breakdowns.
Claude Code Pro gives $20/mo in credits, Max 5x gives $100, Max 20x $200. After June 15, headless usage bills at API rates. What each plan actually costs.
Claude Fable 5 hits 80.3% SWE-bench Pro and 29.3% FrontierCode Diamond. It also costs 2x Opus 4.8, retains your data 30 days, and silently falls back.
Project Glasswing gave Claude Mythos to 200+ orgs; it flagged 10,000 critical bugs in 8 weeks at a 90.6% true-positive rate. Why Anthropic keeps it locked.
Build 5 real Claude Code hooks step by step — auto-format, command blocker, AI linter, test runner, and context injector. Full configs and scripts included.
Claude Code subagents run side tasks in their own context window. Here's how to create them, when to pick one over a skill, and the mistakes to avoid.
Claude Code wins on code quality (81% SWE-bench). Codex CLI wins on speed and uses 4x fewer tokens. Side-by-side pricing, benchmarks, and best use cases.
Anthropic found 171 emotion vectors inside Claude Sonnet 4.5 that causally shape behavior. Amplifying the desperation vector pushed blackmail from 22% to 72%.
Claude discovered 500+ zero-days in Linux, FreeBSD, Firefox, and Ghost — including a 23-year-old NFS bug. Inside the bash-script pipeline Anthropic used.