Quality/regression issue
Open
Nobody has claimed this yet.
app
bug
model-behavior
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.5k
- PR merge metrics
- PR metrics pending
Description
What issue are you seeing?
I’m using Codex Desktop with the Sol model on a $200 subscription. The same tasks that previously produced correct results now consistently produce much worse results. This appears to be a model regression, not a prompt issue. Please compare this session with my previous results and verify the model quality.
What steps can reproduce the bug?
usage
What is the expected behavior?
No response
Additional information
No response
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
The report identifies Codex Desktop, the Sol model, and a general “usage” reproduction, but names no files, tests, or code entry points. Start by reviewing the reported session against the user's previous results; done means determining whether the model quality regression can be reproduced and verified.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, desktop
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100