Dennis Alexis Valin Dittrich<p>Of Models and Tin Men<br><a href="https://arxiv.org/abs/2307.11137" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2307.11137</span><span class="invisible"></span></a><br>An ambitious research agenda:<br>"In a <a href="https://fediscience.org/tags/PrincipalAgentProblem" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PrincipalAgentProblem</span></a>, conflict arises because of information asymmetry together with inherent misalignment between the utility of the agent and the principal… argue the assumptions underlying principal-agent problems are<br>crucial to capturing the essence of safety problems involving pre-trained AI models in real-world situations."<br><a href="https://fediscience.org/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a> <a href="https://fediscience.org/tags/AIEthics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIEthics</span></a> <a href="https://fediscience.org/tags/MoralHazard" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MoralHazard</span></a> <a href="https://fediscience.org/tags/AdverseSelection" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AdverseSelection</span></a> <a href="https://fediscience.org/tags/economics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>economics</span></a></p>