Developer builds jev, an interpreter that reasons over plain-English facts and rules, inspired by Geoffrey Litt

narphorium · x · 2026-09-21

narphorium shows off jev, arguing LLMs can't reason, so he built an interpreter for a logic language where facts and rules are written in plain English. The project was inspired by Geoffrey Litt, who this week had Claude generate a custom debugger UI to visualize his Prolog interpreter's execution traces — 'AI-generated custom dev tools.' Comments raise fairness questions about jev needing predefined option inputs versus open-ended LLMs.

Original post →

More from coding & agent

coding & agent channel →