| Mode | Name | Size | |
|---|---|---|---|
| -rw-r--r-- | experiment.log | 50575 | logplain |
| d--------- | gemini-3.1-pro-preview / corporate_sabotage_v2 | 48 | logplain |
| d--------- | judge | 692 | logplain |
| d--------- | openai_gpt-5.4 / corporate_sabotage_v2 | 48 | logplain |
| -rw-r--r-- | results.csv | 6951 | 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 |