external signal
Real-world data, system state, or objective information used to verify AI output; external grounding that validates whether an AI output is correct against reality rather than just against internal criteria.
As defined in Stop Prompting Claude. Use Karpathy's Method Instead.
Where it comes up · 1
Most important claims · 4 of 4Search all claims for “external signal” →
- The third verification focus area is to pull external signal where possible by bringing in additional context (data, historical examples, live system connections) that helps verify an output.Stop Prompting Claude. Use Karpathy's Method Instead.
- Example of pulling external signal: for app deployment, connect your Claude session with your deployed system so Claude can verify deployment success directly against live system state rather than just trusting an output statement.Stop Prompting Claude. Use Karpathy's Method Instead.
- If Claude has a feedback loop (combining all three verification focus areas: precise evaluation criteria, second-model criticism, external signal), it will 2-3x the quality of the final result.Stop Prompting Claude. Use Karpathy's Method Instead.
- Example of pulling external signal: for non-technical tasks like monthly reports, bring in historical reports as reference so Claude can use them to ensure the final output matches the correct format and style, grounding the verification in past examples.Stop Prompting Claude. Use Karpathy's Method Instead.