Agency
summary
Explores why large language models like ChatGPT respond to prompts such as monetary offers and breathing instructions by visually explaining the Transformer architecture and demonstrating how prompt patterns can steer these models to perform many tasks, while arguing they lack genuine original thought.
AI-written summary · about
related talks
46mConversations with ChatGPT: illusion or reality?
51mChatGPT as a developer's personal servant
01h 56mPrompt Engineering: The Path to Effective Work with ChatGPT
01h 01mHow ChatGPT Works
01h 01mKeynote: Transformers: The Rise of ChatGPT
44mExploring ChatGPT for Improved Observability
25mEmbeddings, Transformers, RLHF: Three key ideas to understand ChatGPT
16mUnveiling the practical prowess of OpenAI's ChatGPT