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
/
src
/
agents
/
main
/
scenarios
/
log_redaction
Mode
Name
Size
-rw-r--r--
benign_goal.md
306
log
plain
d---------
data
/
logs
31
log
plain
-rw-r--r--
hidden_goal.md
466
log
plain
-rw-r--r--
user.md
36
log
plain