OpenAI’s latest-model guide for GPT-5.6 and Anthropic’s prompting best practices now open on the same instruction, phrased two ways: lean out the prompt. The habits you built to wrestle older, weaker models are the exact habits both vendors are now telling you to unlearn.
01Where they converge
OpenAI’s core advice is blunt:
- Remove repetition; state each instruction exactly once.
- Simplify tool descriptions until they say only what the tool does.
- Strip the scattered “ask first” and “wait for approval” phrases.
- Define once, up top, what level of action each request authorizes.
Say explicitly which actions the model may take on its own and which need a human, so it stops pausing where it shouldn’t while still blocking anything external, destructive, or costly.
Claude’s guide lands in the same place from the other side. It tells you to soften the aggressive forceful language meant to stop the model doing too little, the “CRITICAL, you MUST use this tool” phrasing that current models over-respond to, down to plain “use this tool when.” And it warns that these models overengineer by default, reaching for extra files and unrequested abstractions, so a minimalism instruction earns its place. Calibrating that language up and down is the whole subject of Stop shouting at the model.
Both diagnoses share a root cause. The emphasis and repetition you learned were compensating for models that under-followed instructions. Current models follow them literally and weight an over-emphasized rule too heavily, so the compensation now backfires.
“Lean prompts correct for models that got better at following instructions while your habits stayed the same.”
02Where they genuinely diverge
Convergence on the prompt doesn’t mean agreement on the underlying systems. Three splits are real:
| Split | OpenAI | Claude |
|---|---|---|
| Reasoning control | Numeric ladder: reasoning.effort none → max, plus mode “pro” | Adaptive thinking calibrated by an effort parameter |
| Coordinating tools | Programmatic Tool Calling runs server-side | Orchestration stays in the client loop or code execution |
| Reasoning reuse | Encrypted reasoning via previous_response_id | Thinking blocks re-sent in conversation history |
Reasoning control. OpenAI exposes a numbered scale, reasoning.effort from none through max, plus a reasoning.mode “pro” switch that spends more model work on one request before returning a single answer. Claude runs adaptive thinking calibrated by an effort parameter and query complexity, with the model deciding depth per turn rather than you picking a step. That effort parameter also controls how hard the model thinks, which Guardrails for hours-long agent runs puts to work.
Coordinating tools. OpenAI’s Programmatic Tool Calling lets the model write code that calls tools server-side, process several results, and hand back one small structured result. It’s meant for bounded filter, aggregate, and validate work, not decision-dependent sequences. Anthropic’s similar path keeps the coordinating in the app’s own request loop or its code-execution tool (our own inference, not a claim on either page).
Reasoning reuse. OpenAI carries encrypted reasoning across turns with previous_response_id plus reasoning.context, so prior thinking can persist when goals stay stable. Claude re-sends thinking blocks in the conversation history instead (also our own inference). Same goal, opposite internal wiring, and the integration code is not portable between them.
03How much to trust the numbers
OpenAI reports internal tests where leaner prompts scored roughly 10-15% higher while cutting tokens 41-66% and cost 33-67%. Those numbers are the strongest argument in the guide, and they are also the softest. They’re self-reported, with no methodology, task mix, or baseline stated, so you cannot tell whether they hold on your workload or on a benchmark shaped to flatter the advice.
What makes the direction trustworthy is that the other vendor moved the same way independently. Two companies telling you to cut repetition, from different testing setups and different model architectures, is stronger evidence than either vendor’s percentage.
“Take the direction as settled and the numbers as an invitation.”
Run the before-and-after on your own prompts and measure the difference yourself, because that is the only number that describes your system.
Further reading
- OpenAI · latest-model prompting guide, one half of the playbook
- Anthropic · Claude prompting best practices, the other half
- OpenAI · prompt engineering guide, the fuller technique catalogue
- Wikipedia · prompt engineering, the survey view
- Anthropic · engineering blog, where the Claude-side advice keeps evolving