About 1,210,000 results
Open links in new tab
  1. Coding with Cardboard: Building Physical Models of Data Structures

    Building physical models of data structures using cardboard and other everyday materials can transform abstract concepts into tangible, interactive learning experiences. This hands-on method not only aids in understanding but also makes the …

  2. [2108.07732] Program Synthesis with Large Language Models

    Aug 16, 2021 · Abstract: This paper explores the limits of the current generation of large language models for program synthesis in general purpose programming languages. We evaluate a collection of such models (with between 244M and 137B parameters) on two new benchmarks, MBPP and MathQA-Python, in both the few-shot and fine-tuning regimes.

  3. Prompting Is Programming: A Query Language for Large Language

    Dec 12, 2022 · Based on this, we present the novel idea of Language Model Programming (LMP). LMP generalizes language model prompting from pure text prompts to an intuitive combination of text prompting and scripting. Additionally, LMP allows constraints to be specified over the language model output.

  4. Title: A Systematic Evaluation of Large Language Models of Code

    Feb 26, 2022 · We release a new model, PolyCoder, with 2.7B parameters based on the GPT-2 architecture, which was trained on 249GB of code across 12 programming languages on a single machine. In the C programming language, PolyCoder outperforms all models including Codex.

  5. StarCoder: A State-of-the-Art LLM for Code - Hugging Face

    May 4, 2023 · We found that StarCoderBase outperforms existing open Code LLMs on popular programming benchmarks and matches or surpasses closed models such as code-cushman-001 from OpenAI (the original Codex model that powered early versions of GitHub Copilot).

  6. This week makers are introduced to cardboard engineering and cardboard prototyping. ESSENTIAL QUESTIONS • What is a cardboard prototype? • How do artists, engineers, and makers solve problems when they’re working? LEARNING OUTCOMES 1. Explore how to build and prototype with cardboard. 2. Engage in project-based learning through ...

  7. Making AI-generated code more accurate in any language

    Apr 18, 2025 · It could improve programming assistants, AI-powered data analysis, and scientific discovery tools by ensuring that AI-generated outputs remain both useful and correct,” says João Loula, an MIT graduate student and co-lead author of a paper on this framework.

  8. CS106B Object-Oriented Programming - web.stanford.edu

    2 days ago · Overview: Object-Oriented Programming. Today, we delved into object-oriented programming (OOP), with a focus on classes and objects. This marks a significant transition in the course from taking a mostly client-side view of ADTs to digging into the implementation details behind the scenes and examining how we can create those ADTs in C++.

  9. A New Simple Programming Language for Education

    This paper presents the development of a new small programming language named SIMPLE, "Simple Imperative-Model Programming Language for Education. The motivations for the development of this new language stems from the lack of literature for practical efforts and guidelines to develop programming languages bottom-up from scratch.

  10. Cardboard modeling: exploring, experiencing and communicating

    This chapter presents Cardboard modeling as a tool for design that allows for simultaneous exploration, experiencing, and communication of design proposals. It introduces basic techniques and exercises to build skill and speed in Cardboard modeling and then demonstrates how it can be used as a tool for exploration.

  11. Some results have been removed