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 8, 202624mWatch on YouTube ↗

Episode Details

EPISODE INFO

Released
May 8, 2026
Duration
24m
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 scales inference compute with effort, budgets, adaptive thinking The talk defines test-time compute as spending more inference-time tokens to improve results, showing performance gains both from larger models and from higher effort on the same model.

RELATED EPISODES

Agent identity: A new access model for Claude Tag

Agent identity: A new access model for Claude Tag

Delegate and schedule tasks in Claude Cowork

Delegate and schedule tasks in Claude Cowork

The Briefing: Financial Services

The Briefing: Financial Services

How Anthropic uses Claude in GTM Engineering

How Anthropic uses Claude in GTM Engineering

Code with Claude Tokyo 2026: Opening Keynote

Code with Claude Tokyo 2026: Opening Keynote

The Problem Solvers | Max Junestrand at Legora

The Problem Solvers | Max Junestrand at Legora

Get more out of YouTube videos.

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