ctan d794828c7e docs(phase2): add the optimizer and adversarial-cartography layers ...

The execution tiers answer 'how to run a tactic', not 'which tactic is best'
nor 'where is the danger'. Adds two decision layers: an optimizer over
StrategySpec (objectives incl. tail risk, coarse-to-fine search, LLM as
candidate seeder) and an adversarial cartography (AdversarySpec + alternating
min-max + scenario sweeps + danger frontier + sensitivity), giving the danger
view for BOTH sides. Reframes the LLM as hypothesis generator / red team /
explicator / reporter, never the optimizer or per-turn executor in sweeps.
Adds D12-D14 and phases P3 (optimizer) / P4 (robustness).

2026-09-21 10:27:11 +02:00

..

conformance-srd.md

docs(rules): conformance journal round 15 - nonlethal, splash, skills and flight (out of scope -> modeled)

2026-09-20 22:35:55 +02:00

phase-2-llm-architecture.md

docs(phase2): add the optimizer and adversarial-cartography layers

2026-09-21 10:27:11 +02:00