Tag
A tweet thread listing 25 commonly used but often misunderstood AI concepts, such as tokens, embeddings, RAG, agents, and LoRA.
A tweet shares a link to a clear, accessible explanation of why LLM inference differs from traditional inference, presented in a casual walking video.
A thread explaining the mathematical foundations behind key transformer concepts including attention, scaling factor, backpropagation, gradient descent, cross-entropy loss, RoPE, and RMSNorm.
A tweet recommends a clear explanation of transformers, urging readers to read it twice.
The author describes a talk given at a university about the memory limitations of AI agents, using Christopher Nolan's film Memento as an analogy to explain why agents struggle with memory.
This article explains the architecture of DALL-E, focusing on its transformer component that correlates language with discrete image representations to generate high-quality images from text prompts.