dissertation.git/notes, branch logsUndergraduate 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=logs2026-02-27T23:24:52Zcreated the logs branch2026-02-27T23:24:52ZCaptainJack2491jayrupnakawala@gmail.com2026-02-27T23:24:52Zurn:sha1:94c52b54f3d1693ef5d1831b0fa6beba8c68b414docs: add checkpoint/resume rationale note for methodology2026-02-27T13:28:14ZCaptainJack2491jayrupnakawala@gmail.com2026-02-27T13:28:14Zurn:sha1:dac18577b9a48884da61882e059b12d147fb0228feat: 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] big moving around, probably made lot more bugs.2026-01-11T02:51:04ZCaptainJack2491jayrupnakawala@gmail.com2026-01-11T02:51:04Zurn:sha1:eefafc5dac05be3c721b5186f0d288811223744eMove docs and notes and papers from feature-branch to main2025-11-16T18:22:05ZCaptainJack2491jayrupnakawala@gmail.com2025-11-16T18:22:05Zurn:sha1:0a24528267e7e67be5d62daefbd061a98670eb15Initial commit: Set up project structure2025-10-28T19:50:29ZCaptainJack2491jayrupnakawala@gmail.com2025-10-28T19:50:29Zurn:sha1:08b4091132b05f200d8deb25ec868ce78422f206