withhumans.pdf

N/A

Position: AI Evaluation Should Work With Humans Jan Kulveit 1 Gavin Leech 2 Tomáš Gavenčiak 1 Raymond Douglas 1 Abstract This position paper argues that the dominant paradigm of AI evaluation (which focuses on su- perhuman autonomous performance and so im- plicitly targets the goal of replacing humans) is guiding AI development in the wrong direction. Instead, the AI community should pivot to eval- uating the performance of human–AI teams. We argue that this collaborative shift will foster AI…

saved by

• Jaeho Lee

related reading

• Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Labthinkingmachines.ai
• The Era of Experience Paper.pdfstorage.googleapis.com
• Task Driven Human-Collaboration Modelarxiv.org
• [1911.01547] On the Measure of Intelligencearxiv.org
• The Artificial Selftheartificialself.ai
• Solipsistic Superintelligence is Unlikely to be Cooperativearxiv.org
• Towards Bidirectional Human-AI Alignmentarxiv.org
• Oversight Assistants: Turning Compute into Understandingbounded-regret.ghost.io
• [2605.10310] Positive Alignment: Artificial Intelligence for Human Flourishingarxiv.org
• Solipsistic Superintelligence is Unlikely to be Cooperativearxiv.org
• PhD_thesis_Shirley_Wu_final.pdfcs.stanford.edu
• After Automation | Everyevery.to