https://github.com/hinanohart/yuragi
One word can break your AI's confidence. yuragi finds which one. LLM confidence fragility analyzer with 17 CLI commands, 9 psychology experiments, and 10 perturbation types.
https://github.com/hinanohart/yuragi
ai-safety cli confidence evaluation llm machine-learning nlp prompt-engineering psychology python
Last synced: 24 days ago
JSON representation
One word can break your AI's confidence. yuragi finds which one. LLM confidence fragility analyzer with 17 CLI commands, 9 psychology experiments, and 10 perturbation types.
- Host: GitHub
- URL: https://github.com/hinanohart/yuragi
- Owner: hinanohart
- License: mit
- Created: 2026-04-10T11:07:48.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2026-04-12T15:05:43.000Z (2 months ago)
- Last Synced: 2026-04-12T16:36:32.297Z (2 months ago)
- Topics: ai-safety, cli, confidence, evaluation, llm, machine-learning, nlp, prompt-engineering, psychology, python
- Language: Python
- Homepage: https://hinanohart.github.io/yuragi
- Size: 4.12 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.ja.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Citation: CITATION.cff
- Codeowners: .github/CODEOWNERS
- Security: SECURITY.md
- Roadmap: ROADMAP.md