3 papers
cs.CY2026
Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment
Roland Pihlakas, Jan Llenzl Dagohoy
Large language models (LLMs) are increasingly deployed as autonomous agents that make sequences of decisions over extended interactions in high-stakes domains. However, the behavio…
cs.CY2025
BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format
Roland Pihlakas, Sruthi Susan Kuriakose
Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser", specific…
cs.AI2022
Improving performance in multi-objective decision-making in Bottles environments with soft maximin approaches
Benjamin J Smith, Robert Klassert, Roland Pihlakas
Balancing multiple competing and conflicting objectives is an essential task for any artificial intelligence tasked with satisfying human values or preferences. Conflict arises bot…