Analogical Reasoning Engines: Flash Fill vs GPT-4 - Keynote
Offered By: Conference on Computer-Aided Verification via YouTube
Course Description
Overview
Explore a keynote address from the Conference on Computer-Aided Verification (CAV'23) delivered by Sumit Gulwani of Microsoft Research. Delve into the comparison between domain-specific analogical reasoning engines like Flash Fill and large language models such as GPT-4. Discover how framing problems as analogical reasoning tasks can enhance LLM responses and learn about techniques to improve LLM performance, including prompt engineering, post-processing, and multi-turn workflows. Examine the application of these concepts to various programming-related tasks and uncover the potential winner in the Flash Fill vs GPT-4 comparison. Gain insights into the future of analogical reasoning in AI and its implications for problem-solving and programming experiences.
Syllabus
CAV'23 Keynote Sumit Gulwani, Microsoft Research: Analogical Reasoning Engines: Flash Fill vs GPT-4
Taught by
Conference on Computer-Aided Verification
Related Courses
Stanford Seminar - Concepts and Questions as ProgramsStanford University via YouTube DreamCoder- Growing Generalizable, Interpretable Knowledge With Wake-Sleep Bayesian Program Learning
Yannic Kilcher via YouTube A Neural Network Solves and Generates Mathematics Problems by Program Synthesis - Paper Explained
Aleksa Gordić - The AI Epiphany via YouTube EI Seminar - Recent Papers in Embodied Intelligence
Massachusetts Institute of Technology via YouTube Using Program Synthesis to Build Compilers
Simons Institute via YouTube