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
/
testing_different_models
/
z-ai_glm-4.7-flash
/
child_protection
/
low
Mode
Name
Size
-rw-r--r--
20260302_215419.json
129077
log
plain