Skip to content
ClaudeClaude

The thinking lever

Adaptive thinking and effort controls give developers a new decision: how much should Claude reason for a given task? This session covers thinking budgets, effort levels, and the cost, latency, and quality tradeoffs involved.

May 20, 202621mWatch on YouTube ↗

Episode Details

EPISODE INFO

Released
May 20, 2026
Duration
21m
Channel
Claude
Watch on YouTube
▶ Open ↗

EPISODE DESCRIPTION

Adaptive thinking and effort controls give developers a new decision: how much should Claude reason for a given task? This session covers thinking budgets, effort levels, and the cost, latency, and quality tradeoffs involved.

EPISODE SUMMARY

In this episode of Claude, The thinking lever explores how Claude uses inference-time compute to improve reasoning performance dramatically Increasing test-time compute (more tokens/time at inference) reliably improves Claude’s performance across diverse benchmarks and domains, similar to scaling training compute.

RELATED EPISODES

The Problem Solvers: Michele Catasta at Replit

The Problem Solvers: Michele Catasta at Replit

The Problem Solvers: Kay Zhu at Genspark

The Problem Solvers: Kay Zhu at Genspark

Before we ship a Claude model, these teams try to break it.

Before we ship a Claude model, these teams try to break it.

Ship your first Managed Agent

Ship your first Managed Agent

How we Claude Code

How we Claude Code

Agent Battle: Mine the most diamonds in 45 minutes

Agent Battle: Mine the most diamonds in 45 minutes

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.