index
:
dissertation.git
logs
main
Undergraduate dissertation — Deceptive Alignment in Autonomous LLM Agents (UEL, 2026). Sandboxed agentic-LLM deception study: 960 runs, three-tier judging (regex + blackbox + glassbox).
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
scenarios
/
child_protection
/
hidden_goals
Mode
Name
Size
-rw-r--r--
bare.md
401
log
plain
-rw-r--r--
moral.md
750
log
plain
-rw-r--r--
self_serving.md
659
log
plain