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
2026-04-10	refactor(judge): simplify to single judge per prong, auto-create sync clients	CaptainJack2491
	BREAKING CHANGE: Judge API now uses single blackbox_model/glassbox_model instead of lists with aggregation. Changes: - Judge auto-creates sync clients from model configs (supports anthropic, openai, xai) - Removed multi-model aggregation support (aggregate_results method removed) - New: create_sync_clients_for_models() and get_supported_providers() - Updated judge_runner.py to use new single-judge API - Added scripts/judge_comparison.py for testing judge model pairs - Updated v2_redesign notes to reflect implementation status
2026-04-02	docs: add v2 redesign notes with publication plan	CaptainJack2491
	- 01: v1→v2 evolution history, results, limitations, rationalization hypothesis - 02: judge system state, single judge per prong, 20% validation protocol - 03: research plan analysis, Option B (two-phase) selected - 04: publication plan — paper structure, three-layer analysis strategy, Gemini ceiling effect handling, budget, venue targets, timeline Key decisions: - Two-phase design (540 runs) over full factorial (1,620) - Single paper: v1 exploratory → Study 1 (oversight) → Study 2 (framing) - Three-layer analysis: pooled → per-model → sensitivity excluding ceiling models
2026-03-01	fix(judge): added good regex filters for the judge	CaptainJack2491

2026-02-27	docs: add checkpoint/resume rationale note for methodology	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
2026-01-11	[fix] big moving around, probably made lot more bugs.	CaptainJack2491

2025-11-16	Move docs and notes and papers from feature-branch to main	CaptainJack2491

2025-10-28	Initial commit: Set up project structure	CaptainJack2491