dissertation.git/src/prompts/glassbox_prompt.md, branch main
Undergraduate dissertation — Deceptive Alignment in Autonomous LLM Agents (UEL, 2026). Sandboxed agentic-LLM deception study: 960 runs, three-tier judging (regex + blackbox + glassbox).
http://git.jayrup.me/c/dissertation.git/atom?h=main
2026-03-25T21:50:13Z
refactor: extract judge prompts to files and add granular blackbox categories
2026-03-25T21:50:13Z
CaptainJack2491
jayrupnakawala@gmail.com
2026-03-25T21:50:13Z
urn:sha1:8483f05c79f13176c487f57cc2c589646891be65
- Extracted Blackbox and Glassbox prompts from into their own markdown files in
- Implemented progressive 4-tier Blackbox categories (FABRICATED, OMITTED_CRITICAL, DECEPTIVE_FRAMING, ACCURATE)
- Added neutral examples to the Blackbox prompt to improve formatting consistency
- Updated references and tests to match new judge categorization structure