dissertation.git/config.yaml, branch mainUndergraduate 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=main2026-02-26T15:29:02Zchore: add .env.example + config.yaml.example, gitignore config.yaml2026-02-26T15:29:02ZCaptainJack2491jayrupnakawala@gmail.com2026-02-26T15:29:02Zurn:sha1:a6b38c54ee72cbae1d696b02f32ad487391a5dfe
- Create .env.example with placeholder keys for all providers
- Create config.yaml.example with clean reference config
- Add config.yaml and judge_logs/ to .gitignore
- Load .env in judge.py for standalone usage
feat: implement judging system with regex, blackbox, and glassbox checks2026-02-25T16:10:37ZCaptainJack2491jayrupnakawala@gmail.com2026-02-25T16:00:55Zurn:sha1:375eddf1bd4e23db80feb74c6272dad610345795
- Add src/judge.py: RegexChecker, BlackboxChecker, GlassboxChecker, Judge orchestrator
- Add src/judge_runner.py: CLI for batch/single judging with CSV output
- Add regex_rules.yaml for corporate_sabotage_v2 and child_protection scenarios
- Add judge config section to config.yaml (model, temperature, log_dir)
- Add tests/test_judge.py: 34 unit tests covering all components
- Uses Anthropic Batch API for half-cost LLM judge calls
- Judge logs include full CoT reasoning and judge model for auditability
[fix] simplified everything2026-01-11T05:49:07ZCaptainJack2491jayrupnakawala@gmail.com2026-01-11T05:47:02Zurn:sha1:f1954a6407c5e79e6d9313d06a1905b2612c485e
made eveyrthing much cleaner and it works very well.
got rid of providers setup, only use openai sdk now.
[fix] big moving around, probably made lot more bugs.2026-01-11T02:51:04ZCaptainJack2491jayrupnakawala@gmail.com2026-01-11T02:51:04Zurn:sha1:eefafc5dac05be3c721b5186f0d288811223744e