본문으로 건너뛰기

Understanding LLMs for Code Generation

Explore the role of LLMs for coding tasks, focusing on hands-on examples that demonstrate effective prompt engineering techniques to optimize code generation.
Andrea Valenzuela
Josep Ferrer
Andrea Valenzuela, Josep Ferrer

무료 계정 만들기

실습 문제하고 트랙하세요.

Google로 계속하기계속 진행하시면 다음 사항에 동의하는 것으로 간주됩니다: 이용약관 및 개인정보 처리방침 그리고 귀하의 데이터가 미국에 저장된다는 점에 동의하는 것으로 간주됩니다.

함께 코드 따라하기

코드 따라하기 ↗
슬라이드 보기 ↗

Over the past year, Large Language Models (LLMs) have showcased remarkable natural language capabilities, setting new standards in Natural Language Processing and fueling the development of LLM-powered applications. As interest in leveraging LLMs for coding tasks continues to grow, companies are pushing the boundaries by transforming natural language into code generation, resulting in products like GitHub Copilot.

In this session, Andrea and Josep will explore the role of LLMs for coding tasks, focusing on hands-on examples that demonstrate effective prompt engineering techniques to optimize code generation. Whether you're interested in understanding how models work for coding or looking for ways to streamline your coding workflow, this session will provide with the insights and practical skills to fully utilize the potential of LLMs for coding.

Key Takeaways:

  • Learn how large language models generate text.
  • The inherent challenges of LLMs for code generation.
  • Prompt engineering strategies for code generation.

Resources

주제

Artificial IntelligenceGenerative AIDataLab

관련

블로그

Top 20 LLM Guardrails With Examples

더 보기 →