New ask Hacker News story: Ask HN: Video showing LLM assitent coding on big code base
Ask HN: Video showing LLM assitent coding on big code base
2 by CopyOnWrite | 0 comments on Hacker News.
As a experienced software developer I read a lot about how AI tools make coding faster and speed up development of software. In my personal experience, LLMs help with: - answering questions - generating simple code/scaffolding in a vacuum At the same time I don't have much success using LLMs to generate code in a simple CRUD application (around 20K LOC). What I am looking for, is a video showing w/o time lapses/breaks, how an experienced prompt engineer uses an LLM to add a non trivial feature to a code base with at least 20K LOC. What I am looking for: - It must be used to add a feature on a bigger code base (>= 20 LOC) - The added feature cannot be a leaf feature (means it must integrate with the rest of the system at multiple points) - The prompting has to be less effort/faster than to type the solution in the programming language - Any programming language/framework is fair game - Any LLM is fair game - The code base can be a bigger open source project (since I assume all LLMs were trained on open source projects, this should make it easier for LLMs to perform)
2 by CopyOnWrite | 0 comments on Hacker News.
As a experienced software developer I read a lot about how AI tools make coding faster and speed up development of software. In my personal experience, LLMs help with: - answering questions - generating simple code/scaffolding in a vacuum At the same time I don't have much success using LLMs to generate code in a simple CRUD application (around 20K LOC). What I am looking for, is a video showing w/o time lapses/breaks, how an experienced prompt engineer uses an LLM to add a non trivial feature to a code base with at least 20K LOC. What I am looking for: - It must be used to add a feature on a bigger code base (>= 20 LOC) - The added feature cannot be a leaf feature (means it must integrate with the rest of the system at multiple points) - The prompting has to be less effort/faster than to type the solution in the programming language - Any programming language/framework is fair game - Any LLM is fair game - The code base can be a bigger open source project (since I assume all LLMs were trained on open source projects, this should make it easier for LLMs to perform)
Comments
Post a Comment