# GPT-4

Date: 14 March 2023 · Era: VI · Everyone · Category: model · Significance: 5/5
People: Sam Altman, Greg Brockman, Ilya Sutskever, Jakub Pachocki
Organisations: OpenAI

Canonical: https://shapeofintelligence.com/timeline/2023-gpt-4/ · Dataset and text CC BY 4.0

> OpenAI's fourth model passes the bar exam in the top ten percent, reads images, and ships in ChatGPT the same day; the laboratory discloses nothing about how it was built.

## What had to happen

49 events back to 1943, oldest first. Direct influences are marked *direct*.

- [1943 · A logical calculus of nervous activity](https://shapeofintelligence.com/md/timeline/1943-mcculloch-pitts-neuron/)
- [1948 · A mathematical theory of communication](https://shapeofintelligence.com/md/timeline/1948-shannon-information-theory/)
- [1949 · Cells that fire together wire together](https://shapeofintelligence.com/md/timeline/1949-hebb-organization-of-behavior/)
- [1950 · Programming a computer for playing chess](https://shapeofintelligence.com/md/timeline/1950-shannon-chess/)
- [1950 · Computing machinery and intelligence](https://shapeofintelligence.com/md/timeline/1950-turing-computing-machinery/)
- [1958 · The perceptron learns](https://shapeofintelligence.com/md/timeline/1958-perceptron/)
- [1959 · Samuel's checkers program coins 'machine learning'](https://shapeofintelligence.com/md/timeline/1959-samuel-machine-learning/)
- [1960 · ADALINE and the least-mean-squares rule](https://shapeofintelligence.com/md/timeline/1960-adaline-lms/)
- [1965 · Moore's law](https://shapeofintelligence.com/md/timeline/1965-moores-law/)
- [1966 · ELIZA](https://shapeofintelligence.com/md/timeline/1966-eliza/)
- [1969 · Perceptrons](https://shapeofintelligence.com/md/timeline/1969-perceptrons-book/)
- [1970 · Reverse-mode automatic differentiation](https://shapeofintelligence.com/md/timeline/1970-linnainmaa-backprop/)
- [1974 · Werbos applies backpropagation to neural networks](https://shapeofintelligence.com/md/timeline/1974-werbos-backprop/)
- [1980 · The Neocognitron](https://shapeofintelligence.com/md/timeline/1980-neocognitron/)
- [1982 · The Hopfield network](https://shapeofintelligence.com/md/timeline/1982-hopfield-network/)
- [1985 · The Boltzmann machine](https://shapeofintelligence.com/md/timeline/1985-boltzmann-machine/)
- [1986 · Backpropagation](https://shapeofintelligence.com/md/timeline/1986-backpropagation/)
- [1988 · Temporal-difference learning](https://shapeofintelligence.com/md/timeline/1988-temporal-difference-learning/)
- [1989 · Q-learning](https://shapeofintelligence.com/md/timeline/1989-q-learning/)
- [1989 · LeNet reads handwritten postcodes](https://shapeofintelligence.com/md/timeline/1989-lenet/)
- [1990 · Finding structure in time](https://shapeofintelligence.com/md/timeline/1990-elman-network/)
- [1991 · The vanishing gradient problem](https://shapeofintelligence.com/md/timeline/1991-vanishing-gradient/)
- [1992 · TD-Gammon reaches world-class backgammon](https://shapeofintelligence.com/md/timeline/1992-td-gammon/)
- [1997 · Long short-term memory](https://shapeofintelligence.com/md/timeline/1997-lstm/)
- [1998 · MNIST and LeNet-5](https://shapeofintelligence.com/md/timeline/1998-mnist-lenet5/)
- [1999 · The first GPU](https://shapeofintelligence.com/md/timeline/1999-geforce-256/)
- [2003 · A neural probabilistic language model](https://shapeofintelligence.com/md/timeline/2003-neural-language-model/)
- [2006 · Deep belief networks and the word 'deep'](https://shapeofintelligence.com/md/timeline/2006-deep-belief-nets/)
- [2007 · CUDA](https://shapeofintelligence.com/md/timeline/2007-cuda/)
- [2009 · Deep learning moves to GPUs](https://shapeofintelligence.com/md/timeline/2009-gpu-deep-learning/)
- [2009 · ImageNet](https://shapeofintelligence.com/md/timeline/2009-imagenet/)
- [2010 · Rectified linear units](https://shapeofintelligence.com/md/timeline/2010-relu/)
- [2012 · Google Brain's network discovers cats](https://shapeofintelligence.com/md/timeline/2012-google-brain-cat/)
- [2012 · Dropout](https://shapeofintelligence.com/md/timeline/2012-dropout/)
- [2012 · AlexNet wins ImageNet](https://shapeofintelligence.com/md/timeline/2012-alexnet/)
- [2013 · Deep Q-networks play Atari](https://shapeofintelligence.com/md/timeline/2013-dqn/)
- [2014 · Attention](https://shapeofintelligence.com/md/timeline/2014-bahdanau-attention/)
- [2014 · Sequence to sequence learning](https://shapeofintelligence.com/md/timeline/2014-seq2seq/)
- [2015 · Batch normalisation](https://shapeofintelligence.com/md/timeline/2015-batchnorm/)
- [2015 · Residual networks](https://shapeofintelligence.com/md/timeline/2015-resnet/)
- [2017 · Attention is all you need](https://shapeofintelligence.com/md/timeline/2017-attention-is-all-you-need/)
- [2017 · Deep reinforcement learning from human preferences](https://shapeofintelligence.com/md/timeline/2017-rl-from-human-preferences/)
- [2018 · GPT: generative pre-training](https://shapeofintelligence.com/md/timeline/2018-gpt-1/)
- [2019 · GPT-2 and the model too dangerous to release](https://shapeofintelligence.com/md/timeline/2019-gpt-2/)
- [2020 · Scaling laws for neural language models](https://shapeofintelligence.com/md/timeline/2020-scaling-laws/) *direct*
- [2020 · GPT-3](https://shapeofintelligence.com/md/timeline/2020-gpt-3/)
- [2020 · Learning to summarise from human feedback](https://shapeofintelligence.com/md/timeline/2020-rlhf-summarisation/)
- [2022 · InstructGPT](https://shapeofintelligence.com/md/timeline/2022-instructgpt/) *direct*
- [2022 · ChatGPT](https://shapeofintelligence.com/md/timeline/2022-chatgpt/) *direct*

GPT-4 was released on 14 March 2023, three and a half months after ChatGPT, and the gap between it and everything else was the largest the field had seen since AlexNet. It scored in the top ten percent on a simulated bar exam where GPT-3.5 had been in the bottom ten, passed most advanced-placement exams, and could describe a photograph or explain why a picture was funny. Microsoft, which had funded its training, confirmed that Bing had been running it for a month.

The technical report was 100 pages and disclosed neither the model's size nor its data nor its architecture, citing competition and safety. The company founded to be open had become, in its critics' phrase, ClosedAI, and the report's authors defended the choice. A section on the scaling laws showed that the model's final loss had been predicted, before training, from runs a ten-thousandth of its size.

GPT-4 held the top of every leaderboard for over a year, and its release, with Microsoft's Copilot products, Google's Bard and the pause letter within the same fortnight, is the moment the frontier became a race between companies rather than a research field. Later reporting put its training compute at more than 10²⁵ floating-point operations, the threshold the EU AI Act would adopt for systemic risk.

## What it led to

20 events downstream, through 2026.

Built on it directly:

- [2023 · 'Pause Giant AI Experiments'](https://shapeofintelligence.com/md/timeline/2023-pause-letter/)
- [2023 · Hinton leaves Google to warn about AI](https://shapeofintelligence.com/md/timeline/2023-hinton-leaves-google/)
- [2023 · The US executive order on AI](https://shapeofintelligence.com/md/timeline/2023-executive-order-14110/)
- [2023 · The Bletchley Declaration](https://shapeofintelligence.com/md/timeline/2023-bletchley-declaration/)
- [2023 · Gemini](https://shapeofintelligence.com/md/timeline/2023-gemini/)
- [2024 · GPT-4o talks](https://shapeofintelligence.com/md/timeline/2024-gpt-4o/)
- [2024 · The EU AI Act enters into force](https://shapeofintelligence.com/md/timeline/2024-eu-ai-act/)
- [2024 · o1 and reasoning models](https://shapeofintelligence.com/md/timeline/2024-o1/)
- [2025 · GPT-5](https://shapeofintelligence.com/md/timeline/2025-gpt-5/)

And, through them, by era:

- VII · Agents: 11 events

## Sources

- [GPT-4 Technical Report (arXiv:2303.08774)](https://arxiv.org/abs/2303.08774) — paper
- [GPT-4 (OpenAI research, 14 March 2023)](https://openai.com/index/gpt-4-research/) — announcement

---

The Shape of Intelligence by Jamie McKaye (https://jamiemckaye.com) · Markdown mirror of https://shapeofintelligence.com/timeline/2023-gpt-4/

Before: [2023 · Claude](https://shapeofintelligence.com/md/timeline/2023-claude/) · After: [2023 · 'Pause Giant AI Experiments'](https://shapeofintelligence.com/md/timeline/2023-pause-letter/)
