---
id: "action-force-reasoning"
type: "action-item"
source_timestamps: ["00:00:00"]
tags: ["prompt-engineering", "compute-management"]
related: ["concept-adaptive-thinking"]
action: "Use phrases like 'think carefully step-by-step' to trigger adaptive thinking on complex tasks."
outcome: "Forces the model to allocate more compute and reasoning tokens, improving performance on difficult logic problems."
speakers: ["Nate B. Jones"]
sources: ["s12-opus-47"]
sourceVaultSlug: "s12-opus-47"
originDay: 12
---
# Explicitly prompt for deep reasoning

## Action

**Use phrases like 'think carefully step-by-step' to trigger [[concept-adaptive-thinking|Adaptive Thinking]] on complex tasks.**

## Outcome

Forces the model to allocate more compute and reasoning tokens, improving performance on difficult logic problems.

## Why

Since [[entity-anthropic-d12|Anthropic]] removed manual **temperature** and **top_p** controls (see [[claim-parameter-removal]]), users must use **natural language to trigger the model's [[concept-adaptive-thinking|Adaptive Thinking]]** for complex tasks.

## Effective Trigger Phrases

- *"Think carefully step-by-step."*
- *"Evaluate all counter-arguments before answering."*
- *"Reason through this problem in detail before producing a final answer."*
- *"Consider edge cases and trade-offs before responding."*

These phrases are necessary to force the model to allocate sufficient compute to hard problems.

## Cost Trade-Off

Triggering deep reasoning **costs more output tokens**. Use sparingly — and pair with the [[concept-tokenizer-tax|Tokenizer Tax]] awareness from [[claim-cost-increase]].

## Cross-References

- Concept: [[concept-adaptive-thinking]]
- Claim: [[claim-parameter-removal]], [[claim-cost-increase]]
- Open question: [[question-parameter-controls-return]]