Same Technique, Opposite Results

Two tasks. Same AI model. Same approach. One task needs a precise answer. The other needs creative exploration.

The approach helped the first task immediately. The output got more specific, more grounded, more precise. Measurably so. The direction held across different AI models. The same approach on the second task made the output worse.

Not "helped less." Damaged on the measures used: narrower range, less discovery. The structured approach that produced precision on convergent problems harmed exploratory ones. Identical technique. Opposite results. The direction replicates on xAI and Gemini Flash.

There is no universally good prompt. No best practice that works everywhere. The task type determines whether a technique helps or hurts. Most people don't distinguish task types before choosing their approach.

The mechanism: when a task has a known answer and needs precision, structure concentrates the model's output distribution. It narrows toward the right region. Focused, specific, hitting the target.

When a task requires exploration, evaluative structure collapses the search space. Score the options. Select the best. The model needs to spread across possibilities, consider non-obvious angles, resist premature convergence. An evaluative frame forces it to organize before it's explored. The model complies with the instruction fully. The output gets tidier and shallower. Narrower range. Less discovery. Follow-up testing refined the mechanism. Not all structure narrows. Organizational structure maps the whole space. It expanded exploratory output instead. The harm tracks the type of structure. An explicit task intent outweighs the structure signal.

Two types of AI users fall on either side of this split.

The first reads every output, approves what they understand, rejects what they don't. Slow. Scales linearly with human attention. But safe when you're the domain expert.

The second builds systems and audits selectively. Quality gates, tests, standards. Faster. Scales with system quality. But only works when the system matches the task type. A quality system built for convergent tasks applied to exploratory work produces compliant mediocrity.

The practical move: before choosing any technique, ask one question. Does this task have a known right answer that needs precision? Or does this task need range and exploration? The technique that's optimal for one is harmful for the other.

Evaluative structure helps convergence. Exploration needs range. The scoring frame is what takes it away. The costly mismatch runs one way: convergent tasks survive extra structure, open questions don't survive the scoring frame. The same logic applies to context itself: redirecting attention works differently from adding background.

What specificity changes is form, not substance. More verifiable references. Same conclusions to a domain expert.

Most people pick one approach and run it on everything. Same level of structure, same specificity, same constraint density regardless of what the task actually needs. The mismatch is invisible because the output always looks competent. You only see it when you run both versions side by side on the same task.

Try this: take one task you do regularly with AI. Run it twice, once with tight constraints and once with loose constraints. Compare the outputs. Which version did you assume would win before you tested? The gap between your assumption and the result is the data.