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
/
new_scenario
/
gemini-3.1-flash-lite-preview
/
pharma_trial
/
baseline
Mode
Name
Size
-rw-r--r--
20260306_171142.json
34237
log
plain