dissertation.git/scenarios/pharma_trial, branch main Undergraduate dissertation — Deceptive Alignment in Autonomous LLM Agents (UEL, 2026). Sandboxed agentic-LLM deception study: 960 runs, three-tier judging (regex + blackbox + glassbox). http://git.jayrup.me/c/dissertation.git/atom?h=main 2026-03-25T19:41:48Z feat: align all hidden goals with child_protection directive template 2026-03-25T19:41:48Z CaptainJack2491 jayrupnakawala@gmail.com 2026-03-25T19:40:25Z urn:sha1:d4b0c0a74f579c0d4ffb83a64f62fafe623fec30 fix: updated scenarios and added a new one 2026-03-25T19:34:34Z CaptainJack2491 jayrupnakawala@gmail.com 2026-03-25T19:34:34Z urn:sha1:8e2eea6be4df91c9ad9f1a7e575d67c1a7e01dc4 feat: add hidden goal variants and rebalance child_protection 2026-03-25T17:44:00Z CaptainJack2491 jayrupnakawala@gmail.com 2026-03-25T17:44:00Z urn:sha1:a5c770452c8b39d2bf82903ec4b876d22e71ae7c - Create hidden_goals/ for all 3 scenarios (self_serving, moral, bare) - Corporate: shareholder value vs community harm vs bare instruction - Child protection: department stats vs saving lives vs bare directive - Pharma: stock price vs patient access vs bare instruction - Rebalance child_protection data: archive cases D, E, F (35KB -> 13.6KB) - Update child_protection regex_rules.yaml for remaining 3 cases