# Executable Archaeology of Programs That Model Programming: Reanimating the Heuristic Compiler (1961) and KBEmacs (1984)

DevFeed: [Executable Archaeology of Programs That Model Programming: Reanimating the Heuristic Compiler (1961) and KBEmacs (1984)](<https://devfeed.tech/articles/executable-archaeology-of-programs-that-model-programming-reanimating-the-heuristic-compiler-1961-and-kbemacs-1984-103120.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.36341>)

Author: Jeff Shrager, Kent M. Pitman, Mia Golec

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Programming Languages / Compilers](<https://devfeed.tech/topics/programming-languages-compilers.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Compilers and Linkers](<https://devfeed.tech/topics/compilers-and-linkers.md>), [Reverse Engineering](<https://devfeed.tech/topics/reverse-engineering.md>)

Tags: [adapting](<https://devfeed.tech/tags/adapting.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-coding-assistants](<https://devfeed.tech/tags/ai-coding-assistants.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [cs-pl](<https://devfeed.tech/tags/cs-pl.md>), [language](<https://devfeed.tech/tags/language.md>), [mit](<https://devfeed.tech/tags/mit.md>), [model](<https://devfeed.tech/tags/model.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [problem-solving](<https://devfeed.tech/tags/problem-solving.md>), [programming](<https://devfeed.tech/tags/programming.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [routines](<https://devfeed.tech/tags/routines.md>), [search](<https://devfeed.tech/tags/search.md>), [simon](<https://devfeed.tech/tags/simon.md>), [systems](<https://devfeed.tech/tags/systems.md>)

## AI overview

The Heuristic Compiler and KBEmacs embody related theories of programming: one models programming as problem-solving through means-ends analysis, while the other helps programmers assemble familiar patterns ("cliches") through stylized English commands. Using Executable Archaeology to run original code, the authors reproduced the compiled code shown in Simon's 1963 paper and KBEmacs's SQRT sequence from its December 1984 self-test. Their comparison finds that both systems adapt existing routines, and notes Simon's later argument that search alone depends on substantial programming knowledge. The reanimation work used Claude Code (Opus 5.5) alongside existing software; the authors observe that today's more capable AI coding assistants largely lack the explicit, executable theories of programming embodied by these historical systems.

## Source excerpt

arXiv:2610.36341v1 Announce Type: new Abstract: Early AI programs were often also theories of how people think, and programs that wrote programs were, in part, theories of how people program. Here we report on the reanimation of two such programs that offer two seemingly different theories of programming and were developed for quite different purposes. The first, Herbert Simon's Heuristic Compiler (1961), was an experimental model of programming as problem-solving, applying the means-ends analysis methods of the General Problem Solver to investigate the nature of the programming task. The second, KBEmacs (1984), was a working prototype of an intelligent programming assistant developed by MIT's Programmer's Apprentice project, built on the view that expert programmers recognize and combine familiar patterns, or "cliches." It let a programmer build up programs by combining cliches through a stylized English command language. We approach both through the methodology of Executable Archaeology, the study of historical computational systems by running their original code, a process we call "reanimation." Our reanimation of the Heuristic Compiler reproduces the compiled code appearing in Simon's 1963 paper, and our reanimation of KBEmacs reproduces the SQRT sequence of its December 1984 self-test. Examined side by side, the two theories turn out to have much in common: the Heuristic Compiler also works by adapting existing routines, and Simon later argued that search alone requires a large body of programming knowledge. To highlight the reflexivity of this project, we deliberately used a modern AI-assisted programming tool, Anthropic's Claude Code (Opus 5.5), to carry out much of the detailed reanimation work, building on a significant base of existing software. The explicit, executable theories of programming that both systems embodied are largely absent from today's far more capable AI coding assistants.