목발이 아닌 학습 도구로 Genai를 사용합니다

GenAI is fast changing the modus operandi of software development. But to build good code from AI, you need to combine traditional programming with the new skill of coaxing code from code, otherwise known as prompt engineering.

In the latest episode of Leaders of Code, GitLab Field CTO Lee Faus and Stack Overflow CEO Prashanth Chandrasekar discuss why syntax is becoming less important, how to build better prompts, and why AI should be treated as a learning tool, not a crutch.

Understanding legacy code has always been challenging. Developers need to understand the context of why the code was written and what it does. But AI-assisted development shows us that syntax isn’t the hard part anymore.

In the podcast episode, Faus explains, “The syntax doesn’t matter anymore. And we’re figuring out that the real power of computer science is people’s critical thinking and problem-solving skills. When we sprinkle creativity in, we’re able to do magical things with the computers in front of us.”

Faus suggests that developers should learn languages like Rust and C++ while nurturing AI prompting skills for embedded development as tech evolves to support connected environments with edge computing.

AI development is accelerating with new models like deep research from OpenAI and DeepSeek. Chandrasekar says, “It doesn’t take a lot of imagination to see where this is heading. You have to be building for where the puck is going.” He believes, “Super intelligent agents won’t be fallible, but they can give 80 to 90% of what you need very effectively.”

AI offers far more than automation – it’s a learning and skill growth tool. Faus believes developers who excel at GenAI today are figuring out how to connect and assemble information that can amplify developer capabilities rather than replacing them. Leveraging GenAI in this way can help drive business strategy, refine product-market fit, and prioritize features that support sustainable growth.

Until now, the industry has primarily focused on AI’s automation and productivity benefits. However, Recent researchWharton Professor Ethan Mollick’s research with Procter and Gamble

신속한 유형을 이해하면 결과가 향상됩니다. 시스템 프롬프트 AI 동작을 설정하는 반면 사용자는 특정 작업을 요청합니다. RAG (Respreval-Augmented Generation)를 통해 개발자는 Stack Overflow와 같은 소스의 외부 데이터에 액세스 할 수 있으므로 AI가 명시 적으로 훈련 된 지식에만 의존하기보다는 검증 된 실시간 정보를 제공 할 수 있습니다.

신속한 엔지니어링은 전통적인 프로그래밍과 나란히 작동해야합니다. 프롬프트는 일관된 출력에 대한 역할, 작업 및 제약과의 상호 작용을 구성 할 수 있습니다. 프로그래밍의 공식 구문 및 정밀도와 달리 자연어에 의존합니다. 이로 인해 경험이 적은 엔지니어가 더 쉽게 접근 할 수 있지만 확고한 면책 조항으로 더 쉬운 것은 반드시 더 나을 필요는 없습니다. AI 도구가 향상됨에 따라 신속한 엔지니어링은 귀중하고 전통적인 코딩은 여전히 ​​고성능 시스템에 필수적입니다.

AI 코딩 보조원은 자동 완성 된 이후로 빛을 발전 시켰습니다. 이제 전체 개발주기를 지원하여 기본 수준 코딩을 간소화합니다. Chandrasekar는 숙련 된 개발자가 더 간단한 작업을 자동화하여 복잡하고 정신적으로 집중적 인 프로젝트에 집중할 수 있다고 지적합니다. Github Copilot의 테스트는 얼리 어답터를 보여줍니다[–>completed tasks 55% fasterResearch from McKinseymastery of promptingask the LLM to write its own promptjunior engineersmature into an experienced engineerembrace new ways of workingdevelop useful computer programsresearchStack Overflow PodcastStack Overflow’s Developer Surveytrusted AI codedevelop good code