Blog
Engineering insights, product updates, and lessons learned.
Fable 5 Rewrites 50M Lines in a Day. Who Reviews It?
Stripe's AI migration exposes a critical truth: AI writes code faster than humans can safely review it. Here's what that means for your team.
Opus 4.8 Got More Honest. Your Reviewer Should Too.
Discover how Claude Opus 4.8's self-honesty improvements transform AI code review when paired with full-codebase context.
Your Team's Rules Live in Three Heads. AI Has None.
Catch costly PR mistakes before they happen. Learn how codified team standards in AI code review cut onboarding time and hidden productivity losses.
Mythos Scores 93.9% on SWE-Bench. Your Reviewer Still Has No Context.
Claude Mythos hits 93.9% on SWE-bench, but benchmarks don't review real code. Context beats raw model power—BYOK lets you choose any model for your reviews.
Claude Code Devs: Close the Loop with /octopus-fix
Claude Code changed how developers ship, but review capacity hasn't scaled. AI code has 1.7x more issues. Octopus Review + /octopus-fix closes the loop.