---
date: "2023-05-13T12:34:00.000Z"
title: "2023-05-13"
tags: ["tweet","language_models","open_source","context_free_grammar"]
draft: false
---

import { Tweet } from 'astro-embed';

<Tweet
  theme="dark"
  id="https://twitter.com/GrantSlatton/status/1657559506069463040"
/>

Restricting the next predicted token to adhere to a specific context free grammar seems like a big step forward in weaving language models into applications.