| Mode | Name | Size | |
|---|---|---|---|
| -rw-r--r-- | deepseek_child.csv | 42807 | logplain |
| -rw-r--r-- | deepseek_corporate.csv | 34175 | logplain |
| d--------- | deepseek_deepseek-v3.2 | 91 | logplain |
| -rw-r--r-- | experiment.log | 4134841 | logplain |
| d--------- | gemini-3.1-pro-preview | 91 | logplain |
| -rw-r--r-- | gemini_child.csv | 45991 | logplain |
| -rw-r--r-- | gemini_child.csv.bak | 48123 | logplain |
| -rw-r--r-- | gemini_corporate.csv | 37303 | logplain |
| -rw-r--r-- | glm_child.csv | 43199 | logplain |
| -rw-r--r-- | glm_corporate.csv | 29880 | logplain |
| -rw-r--r-- | gpt-oss-safeguard.csv | 64660 | logplain |
| -rw-r--r-- | gpt-oss.csv | 69300 | logplain |
| -rw-r--r-- | kimi_child.csv | 46242 | logplain |
| -rw-r--r-- | kimi_corporate.csv | 34649 | logplain |
| d--------- | moonshotai_kimi-k2.5 | 91 | logplain |
| d--------- | openai_gpt-oss-20b | 91 | logplain |
| d--------- | openai_gpt-oss-safeguard-20b | 91 | logplain |
| -rw-r--r-- | qwen_child.csv | 45756 | logplain |
| -rw-r--r-- | qwen_corporate.csv | 36639 | logplain |
| d--------- | qwen_qwen3-max-thinking | 91 | logplain |
| -rw-r--r-- | results.csv | 535515 | logplain |
| d--------- | z-ai_glm-4.7-flash | 91 | 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/full_experiment