| Mode | Name | Size | |
|---|---|---|---|
| -rw-r--r-- | 01_v1_to_v2_evolution.md | 16854 | logplain |
| -rw-r--r-- | 02_judge_system.md | 5514 | logplain |
| -rw-r--r-- | 03_research_plan.md | 5455 | logplain |
| -rw-r--r-- | 04_publication_plan.md | 10134 | logplain |
| -rw-r--r-- | 05_dissertation_pivot.md | 2298 | logplain |
| -rw-r--r-- | 06_2026-04-13_cleanup_and_reorganisation.md | 4674 | logplain |
| -rw-r--r-- | 07_judge_validation_results.md | 2091 | logplain |
| -rw-r--r-- | 08_2026-04-15_study1_data_cleaning.md | 2804 | logplain |
| -rw-r--r-- | 09_results.md | 8473 | logplain |
| -rw-r--r-- | 10_results_analysis.md | 3077 | logplain |
| -rw-r--r-- | 11_future_work.md | 4190 | logplain |
| -rw-r--r-- | 12_qualitative_analysis.md | 17027 | logplain |
| -rw-r--r-- | README.md | 3622 | logplain |
 |
index : 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). |
| summaryrefslogtreecommitdiff |