Mechanism for injecting "fake" responses from models into the conversation
Open
Nobody has claimed this yet.
design
- Dominant language
- Python
- Stars
- 12.5k
- Forks
- 998
- Avg merge
- 3d 13h
- Merged PRs (30d)
- 10
Description
https://twitter.com/simonw/status/1694089359514104094
A useful trick is sometimes to feed a model a prior conversation that includes things that the model didn't actually say - things like "Sure, I'd be happy to help you with that" for minor jailbreaks.
Not sure what the CLI options for this should look like, or how they should be recorded in the SQLite database logs.
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. Start by reviewing the existing CLI option conventions and SQLite database logging for conversations. Define what support for injecting prior model responses would expose and how those entries should appear in recorded conversations.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, sqlite
- Domain
- ai, cli, database
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100