meta-pytorch / meta-pytorch/KernelAgent
Regarding the choice of large language models?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 556
- Forks
- 92
- PR merge metrics
- No merged PRs in 30d
Description
I am curious whether switching to another LLM—such as DeepSeek-v3.2 or Qwen3—would yield similar results. Additionally, I wonder whether the reported 100% accuracy reflects the outcome of a single execution or the result averaged over multiple experimental runs.
Contributor guide
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
No files, tests, or entry points are named. First clarify whether the request is to compare DeepSeek-v3.2 or Qwen3, to explain the reported 100% accuracy, or both; then identify the evaluation procedure and define the number of runs and reporting format needed for the comparison.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100