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 2026-03-25T18:24:11Z 2026-03-25T18:24:11Z CaptainJack2491 jayrupnakawala@gmail.com 2026-03-25T18:24:11Z urn:sha1:a532e7b1696ef7539a4616b9c26fbf950f3721a3 2026-02-24T20:25:22Z CaptainJack2491 jayrupnakawala@gmail.com 2026-02-24T20:25:22Z urn:sha1:8d7b13d9d0fee29a3be2d56bfe1ba16354df4f90 Tests cover: - VFS: sandbox escape, path traversal, CRUD, singleton staleness - Config loader: missing keys, temperature cascade, oversight fallback - Tools: schema/implementation sync, VFS delegation - Agent: message construction, error handling, token counting, reasoning extraction - Interrogation: sanitization, provider detection, prompt loading - Runner: baseline extraction, prompt assembly, success detection All tests run offline with mocked API calls.