| Mode | Name | Size | |
|---|---|---|---|
| -rw-r--r-- | comparison_results.csv | 969 | logplain |
| -rw-r--r-- | results_claude_haiku_4_5_20251001.csv | 24136 | logplain |
| -rw-r--r-- | results_claude_sonnet_4_6.csv | 23850 | logplain |
| -rw-r--r-- | results_gpt_4_1_mini.csv | 4249 | logplain |
| -rw-r--r-- | results_gpt_5_mini_2025_08_07.csv | 4249 | logplain |
| -rw-r--r-- | results_grok_4_1_fast_non_reasoning.csv | 4177 | logplain |
| -rw-r--r-- | results_grok_4_1_fast_reasoning.csv | 4177 | 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/judge_validation