

Saskia Steinacker
2.3K posts






🎥 Day 1 at #GITEXAFRICA 2024 was a blast! 🙌🏻 From mind-blowing tech demos to inspiring keynotes, here are the top moments that made today unforgettable. We’re just getting started, so gear up for more innovation and excitement tomorrow.



In the future, humans will need to supervise AI systems much smarter than them. We study an analogy: small models supervising large models. Read the Superalignment team's first paper showing progress on a new approach, weak-to-strong generalization: openai.com/research/weak-…








A lot of folks surprised to discover neural nets create implicit spatial maps, based on a paper that came out yesterday. But as you see here from our 2018 course, this has been known for some time! This example is from a 2016 paper which describes a Kaggle gold medal approach.

Do language models have an internal world model? A sense of time? At multiple spatiotemporal scales? In a new paper with @tegmark we provide evidence that they do by finding a literal map of the world inside the activations of Llama-2!