Newest and Lowest Rated Papers
Advanced filtersTopic: AllExperimental
Topic
Topics are auto-detected from title, abstract, and metadata and may be imperfect.
Write code that is easy to delete, not easy to... — programming is terrible
programmingisterrible
Tumblr·2016
Write code that is easy to delete, not easy to extend. “ “Every line of code is written without reason, maintained out of weakness, and deleted by chance” Jean-Paul Sartre’s Programming in ANSI...
No ratings yet
View paper →Humans are very reliable agents
alyssavance
AI Alignment Forum·2022
This post has been recorded as part of the LessWrong Curated Podcast, and an be listened to on Spotify, Apple Podcasts, and Libsyn.
----------------------------------------
Over the last few years, deep-learning-based AI has progressed extremely rapidly in fields like natural language processing and image generation. However, self-driving cars seem stuck in perpetual beta mode, and aggressive predictions there have repeatedly been disappointing. Google's self-driving project started four years before AlexNet kicked off the deep learning revolution, and it still isn't deployed at large scale, thirteen years later. Why are these fields getting such different results?
Right now, I think the biggest answer is that ML benchmarks judge models by average-case performance, while self-driving cars (and many other applications) require matching human worst-case performance. For MNIST, an easy handwriting recognition task, performance tops out at around 99.9% even for top models; it's not very practical to design for or measure higher reliability than that, because the test set is just 10,000 images and a handful are ambiguous. Redwood Research, which is exploring worst-case performance in the context of AI alignment, got reliability rates around 99.997% for their text generation models.
By comparison, human drivers are ridiculously reliable. The US has around one traffic fatality per 100 million miles driven; if a human driver makes 100 decisions per mile, that gets you a worst-cas...
No ratings yet
View paper →Why Simulator AIs want to be Active Inference AIs
Jan_Kulveit, rosehadshar
AI Alignment Forum·2023
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 the second cave. [1] The only way it can learn about the real world is by listening to the conversations of the humans in the first cave, and predicting the next word.
Now imagine that more and more of the conversations GPT overhears in the first cave mention GPT. In fact, more and more of the conversations are actually written by GPT.
As GPT listens to the echoes of its own words, might it start to notice “wait, that’s me speaking”?
Given that GPT already learns to model a lot about humans and reality from listening to the conversations in the first cave, it seems reasonable to expect that it will also learn to model itself. This post unpacks how this might happen, by translating the Simulators frame into the language of predictive processing, and arguing that there is an emergent control loop between the generative world model inside of GPT and the external world.
Simulators as (predictive processing) generative models
There’s a lot of overlap between the concept of simulators and the concept of generative world models in predictive processing. Actually, in my view, it's hard to find any deep conceptual difference - simulators broadly are generative mode...
No ratings yet
View paper →