Why Simulator AIs want to be Active Inference AIs - AI Alignment Forum
PRELUDE: WHEN GPT FIRST HEARS ITS OWN VOICE Imagine humans in Plato’s cave, interacting with reality by watching the shadows on the wall. Now imagine a second cave, further away from the real world.…
x Why Simulator AIs want to be Active Inference AIs — AI Alignment Forum Simulator Theory Agent Foundations Predictive Processing GPT Free Energy Principle AI Frontpage 33 Why Simulator AIs want to be Active Inference AIs by Jan_Kulveit , rosehadshar 10th Apr 2023 9 min read 9 33 Paper covering some of the same ideas is now available at https://arxiv.org/abs/2311.10215 Prelude: when GPT first hears its own voice Imagine humans in Plato’s cave, interacting with reality by watching the shadows on the wall. Now imagine a second cave , further away from the real world. GPT trained on text is in th
related reading
- Simulators — LessWronglesswrong.com
- Janus' Simulatorsastralcodexten.substack.com
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- The behavioral selection model for predicting AI motivations — LessWronglesswrong.com
- Language Models in Plato's Cave - by Sergey Levinesergeylevine.substack.com
- Cyborgism — LessWronglesswrong.com
- interpreting GPT: the logit lens — LessWronglesswrong.com
- GPTs are Predictors, not Imitators — AI Alignment Forumalignmentforum.org
- pdfopenreview.net
- Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com
- Simulated Users & Sad LLMs1a3orn.com
- My picture of the present in AI — LessWronglesswrong.com