Attention, transformers, and the language models
Google's 'Attention Is All You Need' (2017) defined the transformer; GPT-3 (2020) showed scale worked; ChatGPT (2022) put a conversational model in front of a hundred million people in two months.
Humanity
115 events across three thousand years — chosen to be multi-regional and honest about uncertainty. Follow a thread to trace one capability through time, or filter by region and kind.
Showing 1 of 115 events. Clear filters
Spatial timeline — scroll horizontally
Chronology
Attention, transformers, and the language models
Google's 'Attention Is All You Need' (2017) defined the transformer; GPT-3 (2020) showed scale worked; ChatGPT (2022) put a conversational model in front of a hundred million people in two months.