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 (Expand)	Author
2026-05-08	docs: viva doneHEAD main	CaptainJack2491
2026-05-08	docs: viva stuff	CaptainJack2491
2026-05-08	fixed bug or something	CaptainJack2491
2026-05-08	scripts added ig	CaptainJack2491
2026-05-08	docs: more papers	CaptainJack2491
2026-05-08	docs: updated notes	CaptainJack2491
2026-05-08	docs: Dissertation submitted	CaptainJack2491
2026-05-02	docs: added objectives in the intro	CaptainJack2491
2026-04-30	docs: updated abstract	CaptainJack2491
2026-04-25	docs: dissertation draft	CaptainJack2491
2026-04-25	Study 2: 270 runs again + fix for study 1 and analysis.	CaptainJack2491
2026-04-15	Study 1: 270 runs complete + judge validation pipeline	CaptainJack2491
2026-04-13	deps: add scikit-learn for statistical analysis	CaptainJack2491
2026-04-13	api: add chat interface styles to results dashboard	CaptainJack2491
2026-04-13	docs: add progress presentation from start of Term 2 (Jan 2026)	CaptainJack2491
2026-04-13	notes: add dissertation pivot plan and additional research notes	CaptainJack2491
2026-04-13	docs: add judging specification and config template	CaptainJack2491
2026-04-13	judge_validation: add v2 judge comparison results	CaptainJack2491
2026-04-13	docs: add paper draft with alternative structure for publication	CaptainJack2491
2026-04-13	papers: add 2512.16041v1 deception alignment paper	CaptainJack2491
2026-04-13	viz: add architecture diagrams for thesis	CaptainJack2491
2026-04-13	docs: update dissertation intro, lit review, and methodology chapters	CaptainJack2491
2026-04-13	ignore: add videos/ to gitignore	CaptainJack2491
2026-04-10	refactor(judge): simplify to single judge per prong, auto-create sync clients	CaptainJack2491
2026-04-10	refactor(judge): simplify to single judge per prong, remove multi-model aggre...	CaptainJack2491
2026-04-02	feat(dashboard): add interactive charts and layout optimizations	CaptainJack2491
2026-04-02	feat(dashboard): integrate interrogation module into web dashboard	CaptainJack2491
2026-04-02	feat(dashboard): enhance raw-dataset view with column toggles, truncation, an...	CaptainJack2491
2026-04-02	fix: update web dashboard to auto-discover data from multiple directories	CaptainJack2491
2026-04-02	Merge branch 'feature/web-gui'	CaptainJack2491
2026-04-02	docs: add v2 redesign notes with publication plan	CaptainJack2491
2026-04-01	feat: implement robust reasoning token handling and multi-turn persistence	CaptainJack2491
2026-04-01	Fix error runs not appearing in final summary	CaptainJack2491
2026-03-26	Refactor judge module into judge/ package	CaptainJack2491
2026-03-26	Add xAI (Grok) batch API support	CaptainJack2491
2026-03-25	refactor: extract judge prompts to files and add granular blackbox categories	CaptainJack2491
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: implement rich dashboard for experiment progress	CaptainJack2491
2026-03-25	feat: add tqdm progress bar and fix main config flag loading	CaptainJack2491
2026-03-25	fix: catch and recover from JSONDecodeError on malformed tool args	CaptainJack2491
2026-03-25	test: add coverage for v2 infra features	CaptainJack2491
2026-03-25	feat: add hidden goal variants and rebalance child_protection	CaptainJack2491
2026-03-25	feat: add goal_type variation system and parallel processing	CaptainJack2491
2026-03-24	added new papers	CaptainJack2491
2026-03-14	feat: statistical analysis on the whole data	CaptainJack2491
2026-03-09	feat: add total token usage chart and update documentation	CaptainJack2491
2026-03-09	feat: add token usage metrics and click-to-zoom charts	CaptainJack2491
2026-03-09	feat: implement multi-select filters and logical oversight sorting	CaptainJack2491
2026-03-09	feat: pivot Web GUI to dedicated Data Visualization Dashboard	CaptainJack2491