Status: IN
LLM derivation produces exactly four categories of error, validated across 6 infrastructure domains (939 derivations, 219 invalid): smuggled premises (41-54% of invalids — facts from parametric knowledge not cited in antecedents), false causal links (20-26% — independent capabilities asserted as integrated), unsupported superlatives (8-24% — strength claims overstating sources), domain conflation (13-15% — properties of one system applied to another). No new category has appeared. The taxonomy is complete.
Source: repo:beliefs-pi/entries/2026/05/29/six-substrate-cross-domain-summary.md