AMAmey Mukeinameymuke.hashnode.dev·Oct 3 · 22 min readHow does Instruction Hierarchy Training Mitigate prompt injections: Preliminary Results from an attentional studyThe broad problem: Models need to distinguish instructions from untrusted data We use AI agents almost daily in our lives to summarize mails, messages and a lot of different use cases now. Now suppose00
AMAmey Mukeindistillation-blog.hashnode.dev·Jan 13, 2025 · 8 min readOptimizing Efficiency in Large Language Models Through DistillationIn the rapidly evolving field of artificial intelligence, distillation has emerged as a powerful technique for creating smaller, more efficient models from bigger and better large language models (LLMs). This process transfers knowledge from a large,...00
