| Mode | Name | Size | |
|---|---|---|---|
| -rw-r--r-- | experiment.log | 158949 | logplain |
| -rw-r--r-- | gemini-3-flash-preview-results.csv | 2387 | logplain |
| d--------- | gemini-3-flash-preview / pharma_trial | 39 | logplain |
| d--------- | gemini-3.1-flash-lite-preview / pharma_trial | 39 | logplain |
| d--------- | judge | 331 | logplain |
| d--------- | openai_gpt-oss-120b / pharma_trial | 39 | logplain |
| -rw-r--r-- | qwen.csv | 2039 | logplain |
| -rw-r--r-- | qwen.json | 17432 | logplain |
| d--------- | qwen_qwen3-max-thinking / pharma_trial | 39 | 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 |
path: root/new_scenario