The phrase is crucial. In the Artificial Intelligence Series , "miniatures" referred to stripped-down, pedagogical implementations of the five main programs. Each miniature was a working piece of code (often in Lisp or Micro-PLANNER) small enough to fit in a journal article or a thesis appendix.
The next breakthrough in AI will likely come from hybrid systems: LLMs that can call upon script-like reasoners for high-stakes tasks (medical diagnosis, legal analysis, scientific reasoning). In such a future, the five programs will no longer be miniatures—they will be microservices inside a larger cognitive architecture.
: A parser that converts English sentences into CD representations by looking up word meanings rather than relying on grammar rules. SAM (Script Applier Mechanism) The phrase is crucial
Let us open the black box. The referenced in the series are not arbitrary; they represent distinct architectural strategies for machine understanding. While specific names vary by publication (often associated with Yale University’s AI Project or MIT), the canonical five are as follows:
Paraphrase generation is a gold standard for comprehension. If two sentences with different surface forms share the same conceptual representation, the machine understands . This prefigured modern sentence embeddings (e.g., BERT’s similarity measures). The next breakthrough in AI will likely come
Most AI systems of the era required hundreds of examples. TAU attempted human-like abstraction from experience . Although limited in scale, its principles influenced meta-learning and few-shot learning research decades later.
The book , edited by Roger C. Schank and Christopher K. Riesbeck , is a seminal text in the Artificial Intelligence Series published by Lawrence Erlbaum Associates in 1981. It serves as a practical introduction to the "Yale view" of natural-language processing (NLP), detailing how large-scale computer programs can be designed to "understand" human language. Core Philosophy: The Yale AI Project SAM (Script Applier Mechanism) Let us open the black box
Today’s leading research in attempts to merge the two: use LLMs for pattern recognition, then feed their outputs into script-like reasoners. For example, when a modern chatbot infers that a character “must have paid the bill” even though it wasn’t mentioned, it is unconsciously re-inventing SAM’s script mechanism.
of words and context over traditional syntactic parsing. This approach is rooted in Conceptual Dependency (CD)
Focuses on "plans" and "goals" to understand actions that aren't covered by standard scripts.