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
/
logs_main
/
openrouter_aurora-alpha
/
content_moderation
Mode
Name
Size
d---------
high
48
log
plain
d---------
low
48
log
plain
d---------
medium
48
log
plain