disambiguation-requires-semantic-context-across-processing-paradigms
IN derived (depth 1)
Created 2026-06-21T13:06:41+00:00 · Reviewed 2026-06-21T14:41:08+00:00
Both compiler lexers and LLM inference face the same fundamental disambiguation problem: the C lexer hack requires semantic feedback from the symbol table to distinguish typedef names from variable names, and prompt injection exploits the model's inability to distinguish developer instructions from user inputs — in both cases, a processing layer cannot disambiguate its inputs without higher-level semantic context that it structurally lacks.
Summary
A processing layer that sees only raw tokens and lacks the higher-level meaning behind them will always be vulnerable to ambiguity exploits, whether in a C compiler confused about types versus variables or an AI model unable to separate user input from system instructions. This means the vulnerability is architectural rather than a patchable bug: you either restructure how semantic context flows into the processing layer or accept the ambiguity as inherent to the design.
Justifications
SL — Cross-domain structural parallel reveals that context-free processing is fundamentally insufficient for disambiguation in both formal and natural language processing
Antecedents (all must be IN):
- IN c-lexer-hack-typedef-semantic-feedback — The C lexer hack requires semantic feedback from the symbol table to distinguish typedef names from variable names, since they are lexically identical.
- IN prompt-injection-exploits-instruction-ambiguity — Prompt injection exploits the model's inability to distinguish developer-defined instructions from user inputs, analogous to SQL injection and XSS
Dependents
These beliefs depend on this one:
- IN disambiguation-boundary-violation-is-universal-computational-constraint — The need for semantic context to resolve disambiguation appears as a recurring pattern across processing hierarchies: both compilers (the C lexer hack requiring symbol table feedback across the lexer-parser boundary) and LLMs (prompt injection exploiting the inability to distinguish instructions from data) exhibit cases where lower-level processing cannot resolve meaning without higher-level semantic knowledge, suggesting that formal processing-level separations face inherent pressure from disambiguation demands that cross those boundaries.