Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Code generation plugin: Iterate and refine code generation prompts for LLMs to optimize code outputs #16769

Closed
sct-will opened this issue Jun 12, 2024 · 1 comment

Comments

@sct-will
Copy link

sct-will commented Jun 12, 2024

Prompt engineering to optimize the output code generated will iteration and testing. This issue tracks this effort.

@sct-will sct-will converted this from a draft issue Jun 12, 2024
@sct-will sct-will self-assigned this Jun 12, 2024
@sct-will sct-will added role: dev 🤖 area: AI Used to filter issues in the Carbon for AI project. and removed status: needs triage 🕵️‍♀️ labels Jun 12, 2024
@github-project-automation github-project-automation bot moved this to 🆕 New in Carbon for AI Jun 12, 2024
@tay1orjones tay1orjones removed the area: AI Used to filter issues in the Carbon for AI project. label Jun 13, 2024
@sct-will
Copy link
Author

In progress. Code is being generated with much higher fidelity than before, and with a syntax that is much closer to that of a human's but a good amount of work yet remains to harden the technique and cover an array of boundary conditions.

@sct-will sct-will changed the title LLM POC: Iterate and refine code generation prompts for LLMs to optimize code outputs Code generation plugin: Iterate and refine code generation prompts for LLMs to optimize code outputs Aug 23, 2024
@sct-will sct-will moved this from 🏗 In Progress to ✅ Done in Design to Code Aug 23, 2024
@sct-will sct-will closed this as completed by moving to ✅ Done in Design to Code Aug 23, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
Archived in project
Development

No branches or pull requests

2 participants