Llama 4 Scout
Model with 10 million token context
Episodes
-
#6253: Why Context Windows Stalled at a Million TokensA dense 70B model requires about 328 gigabytes of KV cache to serve a single one-million-token prompt, exceeding the memory of an Nvidia B300 chip. -
#1561: Abliteration: The High-Dimensional Lobotomy of AIDiscover how researchers are surgically removing refusal filters from AI models using a mathematical process called abliteration. -
#371: Beyond the Etch A Sketch: Building Persistent AI MemoryWhy treat AI chats like disposable tissues? Discover how to turn years of prompts into a self-healing, evolving digital brain.