Top postsTop post
Lenses Techno-optimism is the belief that the advancement of technology is generally good and has historically made society better. Techno-pessimism is the opposite belief, that technology has generally made the world worse. Both are lenses, or general ways of looking at the world that bring some aspects of reality into...
This essay is based on the ideas of Roman Yampolskiy’s “AI: Unexplainable, Unpredictable, Uncontrollable.” I am not following his reasoning closely, but rather using it as a jumping off point, and the last section is mostly my own reasoning. TL;DR: Things break. Big things break more bigly. ASI double plus...
(Link to calculator described in post: https://will9371.itch.io/probability-calculator) On the Correct Usage of p(doom) On it's face, p(doom) is a bit of a weird concept. On the one hand, it speaks to global trends regarding future technology involving a lot of unknowns and thus necessarily draws heavily from intuition. On the...
Over the course of this sequence, we've discussed what it means to think of Large Language Models (LLMs) as tools, agents, or simulators: exploring definitions, considering alignment implications, responding to recent developments, hypothesizing where different modes of operation might show up in the network, and speculating how different training methods...
Special thanks to Anders Sandberg for help in developing the core idea of this story, Remmelt for editorial feedback, and to Forrest Landry for identifying the underlying ideas. The Mission You have been tasked with a feasibility and safety analysis for "Project Moonbeam", a plan to seed the Moon with...
In Agents, Tools, and Simulators we outlined what it means to describe a system through each of these lenses and how they overlap. In the case of an agent/simulator, our central question is: which property is "driving the bus" with respect to the system's behavior, utilizing the other in its...
We have already spoken about the differences between tools, agents and simulators and the differences in their safety properties. Given the practical difference between them, it would be nice to predict which properties an AI system has. One way to do this is to consider the process used to train...