Show HN: Eevo – Consequential Decision Model
AI Summary
Upright has developed Eevo, a decision model designed to improve AI alignment by training systems to excel at comparative analysis of consequences, expected value calculations, and modeling overlapping outcomes. The approach aims to create AI systems that can better evaluate the real-world impact of their decisions by focusing on consequential reasoning rather than purely maximizing narrow objectives.
From the source
Hi HN, I'm Juho from Upright. I think we may have stumbled upon an interesting approach to AI alignment.The idea is as follows: 1. train a decision model to be really good at comparative sizing of consequences, expected value problems, and modelling overlap …
The full text couldn't be loaded here (the source may require a subscription).
View original at Uprightproject.com