RSSAmplifier

Blog

Food for thought

Hello, World! In this blog I write posts about things that nourish my mind related to computer science (deep-learning, compilers, ...), LLMs or just math....

lucrbvi.bearblog.devRSS feed ↗2 posts

Latest posts

World Models will push the frontier for LLMs

Large Language Models are trained using the next-token prediction objective. This means that the vocabulary distribution of the model needs to be close to that of the training dataset. This objective is highly effective for language because it is already a discrete and compressed representation of world knowledge. Since the middle of 2024 1 , there has been a push for multimodality support in…

Why Claude Mythos is not AGI

Claude Mythos Preview is not AGI.