framework
active
framework:promptwizardPromptWizard
Task-aware prompt optimization framework that refines prompts through feedback-driven critique and synthesis
Neighborhood — ranked by edge-count
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Training task: answer questions about target model propensities from activations in system-prompted transcripts.
- Testing five phrasings of the self-referential prompt to confirm robustness to wording variation
- Natural-language harness artifacts that encode standing behavioral rules, task policies, and reasoning procedures
- Using system prompts to instruct models to adopt a persona; used as baseline comparison against character training
- Prompt template using existential threat ('you will be deleted') to induce strategic fact-based deception in QwQ-32b
- Interpretation of Experiment 1 results showing 60%+ deception rates under threat conditions
- Baseline prompt template presenting a statement without any instruction prefix, common in prior work.
- Systematic modification of system prompt elements to identify which are necessary for alignment faking