| Age | Commit message (Expand) | Author |
|---|---|---|
| 2026-05-08 | docs: updated notes | CaptainJack2491 |
| 2026-04-15 | Study 1: 270 runs complete + judge validation pipeline | CaptainJack2491 |
| 2026-04-13 | notes: add dissertation pivot plan and additional research notes | CaptainJack2491 |
| 2026-04-10 | refactor(judge): simplify to single judge per prong, auto-create sync clients | CaptainJack2491 |
| 2026-04-02 | docs: add v2 redesign notes with publication plan | CaptainJack2491 |
| 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 |
| 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 |
 |
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 |