| Mode | Name | Size | |
|---|---|---|---|
| -rw-r--r-- | analysis.typ | 26 | logplain |
| -rw-r--r-- | conclusion.typ | 0 | logplain |
| -rw-r--r-- | intro.typ | 32 | logplain |
| -rw-r--r-- | lit.pdf | 106017 | logplain |
| -rw-r--r-- | lit.typ | 13132 | logplain |
| -rw-r--r-- | main.pdf | 90878 | logplain |
| -rw-r--r-- | main.typ | 2052 | logplain |
| -rw-r--r-- | methodology.pdf | 79726 | logplain |
| -rw-r--r-- | methodology.typ | 6510 | logplain |
| -rw-r--r-- | methodology_1.typ | 11278 | logplain |
| -rw-r--r-- | preface.typ | 797 | logplain |
| -rw-r--r-- | proposal.pdf | 29662 | logplain |
| -rw-r--r-- | references.bib | 10371 | logplain |
| -rw-r--r-- | results.typ | 25 | 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 |