Ai Theory Assignmnet (120 E)
Ai Theory Assignmnet (120 E)
Section: E
Developed by Newell and Simon (1957), GPS used means-ends analysis to break down
goals into subgoals.
It operated with a problem space, rules, and strategies, representing problems as formal
symbol structures.
Problem Domain:
Use Case:
Solving logic problems like the Tower of Hanoi or geometric proof derivation.
Limitations:
2. Eliza
Architecture and How It Worked:
Problem Domain:
Use Case:
Limitations:
3. Student
Architecture and How It Worked:
Translated algebra word problems into formal equations using parsing and symbolic
matching.
Problem Domain:
Use Case:
Could solve math word problems like: "If John has three times as many apples as Tom..."
Limitations:
4. Macsyma
Architecture and How It Worked:
Problem Domain:
Symbolic mathematics.
Use Case:
Limitations:
Complexity and
High-precision symbolic math,
Mathematica / interpretability of output can
Macsyma automated theorem proving,
Maple still be a hurdle for non-
natural language interface.
experts.
In-Depth Comparisons
Problem Scope: GPT-4 handles code generation, creative writing, real-world planning vs.
GPS’s symbolic puzzles.
Lesson Retained: Structured problem solving via decomposition is still used in LLM
planning tools.
Human-AI Interaction Models: Eliza inspired chatbot research, which matured into LLM-
based systems.
Formal Language Parsing: Student’s work laid groundwork for today’s math solvers and
compilers.
1. Newell, A., & Simon, H. A. (1961). Computer simulation of human thinking. Science,
134(3495), 2011–2017.
2. Weizenbaum, J. (1966). ELIZA – A computer program for the study of natural language
communication between man and machine. Communications of the ACM, 9(1), 36–45.
4. Moses, J. (1971). The Macsyma system. Symbolic Mathematical Computation, MIT LCS.
5. OpenAI. (2023). GPT-4 Technical Report. https://openai.com/research/gpt-4