Changing what my phone agent was shown beat changing the model

Automated excerpt

On one of them, the weakest model after the fix (14 of 18 runs right) beat the strongest model before it (4 of 18). Every call runs three times per model, and I read every reply the scorer flagged. Before the fix, no model got more than 4 of 18 runs right.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.