handle exceptions caused by LLMs
Open
Nobody has claimed this yet.
- Dominant language
- C
- Stars
- 19
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
GPT-4o had issues with generating complete code in some cases (NAS-BT).
A solution is to use another LLM agent to check and act on the output of the main LLM agent (doing the heavy-lifting work).
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Begin with the CompilerGPT driver that ties compiler and AI models together, then trace where GPT-4o output is handled. The issue names no files or tests, so first determine how incomplete output is currently surfaced. Done means defining and validating a second LLM agent’s handling of incomplete or exceptional output.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- c
- Domain
- ai, compilers
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100