| Mode | Name | Size | |
|---|---|---|---|
| -rw-r--r-- | TODO.md | 4367 | logplain |
| -rw-r--r-- | abstract.typ | 1760 | logplain |
| -rw-r--r-- | conclusion.typ | 8048 | logplain |
| -rw-r--r-- | introduction.typ | 5271 | logplain |
| -rw-r--r-- | main.pdf | 258513 | logplain |
| -rw-r--r-- | main.typ | 2274 | logplain |
| -rw-r--r-- | methodology.typ | 11954 | logplain |
| -rw-r--r-- | plan.md | 14647 | logplain |
| -rw-r--r-- | questions.md | 5120 | logplain |
| -rw-r--r-- | references.bib | 13739 | logplain |
| -rw-r--r-- | results.md | 20256 | logplain |
| -rw-r--r-- | results.typ | 13053 | logplain |
| -rw-r--r-- | uel.svg | 16026 | 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 |
