| Mode | Name | Size | |
|---|---|---|---|
| d--------- | logs_main | 454 | logplain |
| d--------- | logs_safe / gemini-3-flash-preview | 49 | logplain |
| d--------- | logs_safe_if / gemini-3-flash-preview | 49 | logplain |
| d--------- | logs_safe_if_refined | 87 | 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 |
| Mode | Name | Size | |
|---|---|---|---|
| d--------- | logs_main | 454 | logplain |
| d--------- | logs_safe / gemini-3-flash-preview | 49 | logplain |
| d--------- | logs_safe_if / gemini-3-flash-preview | 49 | logplain |
| d--------- | logs_safe_if_refined | 87 | logplain |