Inner Alignment

Applied to How to Control an LLM's Behavior (why my P(DOOM) went down) by Roger Dearnaley 5d ago

Applied to Introduction and current research agenda by quila 13d ago

Applied to Alignment is Hard: An Uncomputable Alignment Problem by Alexander Bistagne 14d ago

Applied to Reaction to "Empowerment is (almost) All We Need" : an open-ended alternative by Ryo 14d ago

Applied to Is Interpretability All We Need? by Roger Dearnaley 20d ago

Applied to Optionality approach to ethics by Ryo 20d ago

Applied to Why small phenomenons are relevant to morality ​ by Ryo 20d ago

Applied to We have promising alignment plans with low taxes by Seth Herd 23d ago

Applied to ​​ Open-ended/Phenomenal ​Ethics ​(TLDR) by Ryo 24d ago

Applied to AI Alignment: A Comprehensive Survey by Stephen McAleer 1mo ago

Applied to Open-ended ethics of phenomena (a desiderata with universal morality) by Ryo 1mo ago

Applied to Thoughts On (Solving) Deep Deception by Arun Jose 1mo ago