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
/
02-sandbox
/
README.md
blob: 37f3396e0fd5c9522f9df1cc36363db9b19bba72 (
plain
)
1
Just testing out differnt methods of giving tools to llms