← Jargon

Jargonmachine learning· 6 claims· 3 episodes

GPT-2

A 1.5 billion parameter transformer-based language model trained on diverse text from the web, capable of generating remarkably coherent multi-sentence passages, used by OpenAI to study capabilities and risks of large language models.

As defined in Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94


Where it comes up · 3

Most important claims · 6 of 6Search all claims for “GPT-2” →