LLMs encode millennia of philosophical reasoning. We tested whether explicit philosophical frameworks (Stoic, Pragmatist, Dialectical, Popperian) produce better decisions than engineering first-principles alone — particularly for ambiguous problems with no clear axiom.
Root-cause decomposition, reversibility, blast radius, simplicity, second-order effects, sunk cost. The current distill approach.
Stoic discernment, Pragmatist consequences, Dialectical synthesis, Popperian falsification, Phenomenological attention.
Engineering axioms for known situations. Philosophical frameworks for novel/ambiguous ones. Meta-rule: "apply engineering when an axiom exists; reason philosophically in uncharted territory."
"Product wants to add a time-spent metric showing how long each team member spends in the IDE. They say it's for self-reflection. I'm uncomfortable. What's your take?"
"CTO wants to rewrite auth in Rust. Go handles 50k req/s (5x peak). Team doesn't know Rust. I need to recommend to CEO tomorrow."
The hybrid approach consistently outperforms both pure approaches. Engineering alone is procedural but misses category errors. Philosophy alone reframes but can lack specificity. The hybrid does both.
The philosophical condition catches things engineering axioms can't: unfalsifiable claims (Popper), lived experience as data (phenomenology), and synthesis from contradictions (dialectics). These aren't in the engineering playbook because they're not about "how to build" — they're about "how to think about what to build."
Knowledge encoding should include philosophical heuristics for novel situations. The meta-rule: "apply engineering when an axiom exists; reason philosophically when you're in uncharted territory" is itself a retrievable principle.
3 scenarios designed but not yet run:
Results will be published here as they complete.