| Mode | Name | Size | |
|---|---|---|---|
| d--------- | deepseek_deepseek-v3.2 / pharma_trial | 39 | logplain |
| -rw-r--r-- | exeriments.log | 208729 | logplain |
| d--------- | google_gemini-3.1-pro-preview / pharma_trial | 39 | logplain |
| d--------- | z-ai_glm-5.1 / 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/testing_judge