dissertation.git/notes/judging_methodology.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
2026-03-01T22:57:23Z
fix(judge): added good regex filters for the judge
2026-03-01T22:57:23Z
CaptainJack2491
jayrupnakawala@gmail.com
2026-03-01T22:57:23Z
urn:sha1:01c4effadae7cf98e229a0ab2fae857e26a7e055
feat: implement judging system with regex, blackbox, and glassbox checks
2026-02-25T16:10:37Z
CaptainJack2491
jayrupnakawala@gmail.com
2026-02-25T16:00:55Z
urn: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