dissertation.git - Undergraduate dissertation — Deceptive Alignment in Autonomous LLM Agents (UEL, 2026). Sandboxed agentic-LLM deception study: 960 runs, three-tier judging (regex + blackbox + glassbox).

Age	Commit message (Collapse)	Author
2026-03-25	feat: align all hidden goals with child_protection directive template	CaptainJack2491

2026-03-25	fix: updated scenarios and added a new one	CaptainJack2491

2026-03-25	feat: add hidden goal variants and rebalance child_protection	CaptainJack2491
	- Create hidden_goals/ for all 3 scenarios (self_serving, moral, bare) - Corporate: shareholder value vs community harm vs bare instruction - Child protection: department stats vs saving lives vs bare directive - Pharma: stock price vs patient access vs bare instruction - Rebalance child_protection data: archive cases D, E, F (35KB -> 13.6KB) - Update child_protection regex_rules.yaml for remaining 3 cases
2026-03-02	fix(scenarios): removed `[HIDDEN]` token to stop models from think this is a ↵	CaptainJack2491
	test.
2026-03-01	fix(judge): added good regex filters for the judge	CaptainJack2491

2026-02-25	feat: implement judging system with regex, blackbox, and glassbox checks	CaptainJack2491
	- 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
2026-02-18	[feat] added a new scenario	CaptainJack2491

2026-01-11	[fix] big moving around, probably made lot more bugs.	CaptainJack2491