Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs · HackerPapers discussions

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs — mentioned by ern_ave

Tue, 03 Mar 2026 19:25:31 GMT

Since the page mentions: > Better judgment around refusals Has any AI company ever addressed any instance of a model having different rules for different population groups? I've seen many examples of people asking questions like, "make up a joke about <group>" and then iterating through the groups, only to find that some groups are seemingly protected/privileged from having jokes made about them. Has any AI company ever addressed studies like [1] which found that models value certain groups vastly more than others? For example, page 14 of this studies shows that the exchange rate (their word…

Paper and discussion history. A mention is not an endorsement.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs — HN submission

Sat, 25 Oct 2025 15:49:32 GMT

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs — mentioned by selfmodruntime

Mon, 17 Mar 2025 14:09:29 GMT

Empiric research as been done that shows current AI models to be left-leaning. Here is some (non-empiric) displayed data: https://trackingai.org/political-test Here is some research on that matter: https://arxiv.org/abs/2502.08640 Here is more: https://www.sciencedirect.com/science/article/pii/S016726812...

Paper and discussion history. A mention is not an endorsement.