AI

Fixed thinking budgets are gone on current Claude models, replaced by adaptive thinking plus an effort level in output_config. This course covers what effort actually controls, which workloads repay raising it, why xhigh became the coding default, and how effort interacts with prompt caching in ways that can quietly destroy your hit rate.

Lesson 1 is free. Subscribe to unlock every course.

Secured checkout

$7.65/mo

cancel anytime

Every course on the platform, 350+ and growing

Quizzes, certificates, and your rank on the leaderboard

New courses added every week at no extra cost

Already have All Access? This is included, no need to subscribe separately.

Subscribe

Have a promo code?

USDC & USDT