prompt-automation-paradox-exemplifies-systematic-theory-gap
IN derived (depth 6)
Created 2026-06-21T11:48:37+00:00 · Reviewed 2026-06-21T14:41:08+00:00
Prompt engineering's paradox — automatable (LLMs generate prompts at human-level quality) yet fundamentally fragile (model-specific, 40%+ accuracy shifts from formatting) — is a microcosm of the field's systematic pattern where engineering capability outpaces theoretical understanding: the field can build tools that generate effective prompts without understanding why they work, mirroring its broader ability to deploy what it cannot formally specify.
Justifications
SL — The prompt paradox is the clearest single-domain exemplar of the field-wide engineering-theory gap, connecting a specific practical observation to the structural meta-pattern (depth 6)
Antecedents (all must be IN):
- IN prompt-optimization-is-paradoxically-automatable-yet-fragile — Prompt engineering is paradoxically both automatable (LLMs generate prompts at human-level quality) and deeply fragile (model-specific, with 40%+ accuracy shifts from minor formatting changes), implying that prompt optimization must be continuous, model-specific, and potentially self-maintaining rather than a one-time engineering effort.
- IN engineering-maturity-systematically-outpaces-theoretical-understanding — The LLM field is systematically characterized by engineering maturity outrunning theoretical understanding — standardized pipelines, reproducible results, and practical compensations consistently succeed at every level of the stack despite fundamental theoretical insufficiency that would normally preclude confidence.
Dependents
These beliefs depend on this one:
- OUT automated-prompt-compilation-could-close-inference-theory-gap — The convergence of automated prompt engineering (LLMs generating human-quality prompts) with declarative LM pipeline compilation (DSPy optimizing multi-step LM programs) could close the systematic theory gap in prompt engineering — transforming inference-time control from craft-dependent tuning into a verifiable, compilable engineering discipline.
- IN prompt-theory-gap-makes-inference-control-structurally-unimprovable — The inference-time control layer's structural self-undermining (prompt fragility compounding with context expansion while authority hierarchies create attack surfaces) may be particularly resistant to incremental improvement: the systematic theory gap exemplified by prompt engineering's paradox (automatable yet fundamentally fragile, with engineering capability outpacing formal understanding) suggests that at least some of the inference layer's vulnerabilities reflect structural properties resistant to formalization rather than straightforward engineering deficits awaiting better solutions.