---
id: "2019-02-14-gpt-2"
url: "https://postcutoff.com/e/2019-02-14-gpt-2/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2019-02-14"
date_precision: day
category: model-release
importance: 4
confidence: high
status: [Confirmed]
sources: 3
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2019-02-14-gpt-2/

# 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.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Better language models and their implications (OpenAI)](https://openai.com/index/better-language-models/) (openai.com, official)
2. [GPT-2: 1.5B release (OpenAI)](https://openai.com/index/gpt-2-1-5b-release/) (openai.com, official)
3. [openai/gpt-2 (code)](https://github.com/openai/gpt-2) (github.com, code)

## Changes

- 2026-09-29 (filed): Created

## Related

- 2020-05-28: [GPT-3 (175B) shows in-context few-shot learning](https://postcutoff.com/e/2020-05-28-gpt-3/index.md)
- 2018-06-11: [OpenAI's GPT-1: generative pre-training of Transformers](https://postcutoff.com/e/2018-06-11-gpt-1/index.md)