OpenAI announces GPT-2 and withholds the full model over misuse concerns
GPT-2, a 1.5B-parameter language model trained on 40GB of web text, generated strikingly coherent paragraphs; OpenAI initially released only smaller versions, citing misuse risk, and released the full model in November 2019.
Key facts
- 1.5 billion parameters
- Trained on WebText (~8M web pages, ~40GB)
- Staged release: full 1.5B model published 5 November 2019
- Paper: 'Language Models are Unsupervised Multitask Learners'
What happened
OpenAI showed that scaling a language model produced zero-shot abilities on many tasks, and experimented with staged, responsible release.
Why it matters
First public glimpse of what scaling LLMs could do and the first major debate over whether to release model weights.
Changelog
- 2026-09-29: created
Related events
- OpenAI's GPT-1: generative pre-training of Transformers ★★★★
- GPT-3 (175B) shows in-context few-shot learning ★★★★★
- OpenAI releases gpt-oss, its first open-weight LLMs since GPT-2 ★★★
Sources (3)
- officialBetter language models and their implications (OpenAI)
- officialGPT-2: 1.5B release (OpenAI)
- codeopenai/gpt-2 (code)
id: 2019-02-14-gpt-2 · updated 2026-09-29 · open in the interactive timeline