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.
More from coding & agent
- Expanso ships an AI agent that reads pod logs and fixes stale labels, riding the #jevops wave — aronchick · 2026-09-21
- Designer's toolkit: live tweakable UI blocks, AI prompts for animated sites, 800+ real sites for coding agents — GCWebDesigner · 2026-09-21
- One token is all you need: hacking LLMs into classifiers with logit_bias and max_tokens=1 — AAAzzam · 2026-09-21
- Expanso Builds a Jev-Based Agent That Reads Pod Logs and Auto-Fixes Stale Kubernetes Labels — aronchick · 2026-09-21
- Turning GPT-6 Astra Into a Motion Graphics Studio: 5 Ad Renders in 18 Minutes — PrajwalTomar_ · 2026-09-21
- Sentry CEO: if your product isn't headless, you're investing in the wrong things — zeeg · 2026-09-21