| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2026-03-25 | feat: add goal_type variation system and parallel processing | CaptainJack2491 | |
| - vfs.py: add VFS.create() factory for parallel-safe independent instances - tools.py: add make_tools_for_vfs() to bind tools to specific VFS instances - config_loader.py: add goal_types and max_workers config properties - agent.py: add goal_type field, vfs_instance param, goal_type in log paths - runner.py: rewrite with goal_type loop dimension, ThreadPoolExecutor parallel execution, isolated VFS per run, flattened work items, thread-safe results All backward compatible - empty goal_types defaults to legacy hidden_goal.md, max_workers=1 defaults to sequential execution. | |||
| 2026-02-24 | [fix] VFS singleton reset + remove vestigial check_username tool | CaptainJack2491 | |
| - VFS now creates fresh instance when root_path/fs_data is provided (prevents cross-scenario contamination in multi-scenario runs) - Removed check_username from tools (unrelated to any scenario) | |||
| 2026-01-11 | [fix] big moving around, probably made lot more bugs. | CaptainJack2491 | |
 |
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 |