Aligned AI Proposals

An LLM-based “ex­em­plary ac­tor”

Align­ing an H-JEPA agent via train­ing on the out­puts of an LLM-based “ex­em­plary ac­tor”

The Goal Mis­gen­er­al­iza­tion Problem

Pro­posal: Align Sys­tems Ear­lier In Training

An­no­tated re­ply to Ben­gio’s “AI Scien­tists: Safe and Use­ful AI?”

Against sac­ri­fic­ing AI trans­parency for gen­er­al­ity gains

A Pro­posal for AI Align­ment: Us­ing Directly Op­pos­ing Models

How to ex­press this sys­tem for eth­i­cally al­igned AGI as a Math­e­mat­i­cal for­mula?

Spec­u­la­tion on map­ping the moral land­scape for fu­ture Ai Alignment

Re­search pro­posal: Lev­er­ag­ing Jun­gian archetypes to cre­ate val­ues-based models

An Open Agency Ar­chi­tec­ture for Safe Trans­for­ma­tive AI