GPT
GPT (Generative Pre-trained Transformer) is a series of large-scale pre-trained language models developed by OpenAI, built on the Transformer architecture. The models are trained via unsupervised pre-training on large text corpora and subsequently fine-tuned for specific applications. They support a range of natural language tasks including text completion, question answering, summarization, translation, and code generation, and are among the most representative foundation models in natural language processing.
Core Facts
Large language models such as GPT and BERT are based on the self-supervised learning paradigm
The in-context learning capability of Few-Shot prompting was first systematically described in the GPT-3 paper.
The core working principle of large language models such as GPT-4, Claude, and Gemini is next-token prediction based on the Transformer architecture.
Timeline (last 90 days)
The training corpora of mainstream models (such as the BPE tokenizer of the GPT series) are mainly English, so they segment English more finely and efficiently.
In Coinbase's benchmark, the newer Opus, Sonnet and GPT versions all underperform the previous version on recall, F1 and amount-weighted recall.
As of October 2026, Claude's and GPT's pricing tiers align almost exactly, both offer a 1-million-token context window, both strictly enforce tool schemas, and both host web search on the server side.
Both Claude and GPT offer a 50% batch discount and a cached input discount.
The author believes that once retries, caching, cost logging, and error handling have been built around one API set, the actual engineering effort to migrate from Claude to GPT or vice versa is about a week, not just a configuration change.
Using Claude or GPT at the Premium tier and above is charged from prepaid credits at full API price from the very first request, and the plan provides no credit subsidy.
The X Subscription plan that new Cursor users enter after registering covers only the Grok series of models by default; Claude and GPT are not within the plan's quota.
The Responses API on most LLM gateways only supports GPT-series models.
Other vendors' models integrated into Cursor (such as the Claude and GPT series) are not included in Grok's shared quota system, but are billed separately in compatible paid plans.
Other models in Cursor, such as the Claude and GPT series, are not included in the joint subscription's shared quota system and must be paid for separately in supported tiers.
40 more timeline events
All Facts (20)
Large language models such as GPT and BERT are based on the self-supervised learning paradigm
90%VerifiedThe in-context learning capability of Few-Shot prompting was first systematically described in the GPT-3 paper.
90%VerifiedThe core working principle of large language models such as GPT-4, Claude, and Gemini is next-token prediction based on the Transformer architecture.
90%VerifiedAzure OpenAI Service provides enterprise customers with the ability to invoke models such as GPT-4, DALL-E, and Whisper in a compliant environment.
85%VerifiedWorkBuddy's interface is very similar to those of Qianwen, Doubao, and GPT.
80%VerifiedGPT is a series of large language models developed by OpenAI based on the Transformer architecture
80%VerifiedThe GPT series uses tiktoken (based on BPE encoding) for tokenization.
80%VerifiedThe GPT series uses the Decoder-only variant of the Transformer, predicting the next Token autoregressively.
80%VerifiedVLMs (Vision Language Models) typically consist of a visual encoder (such as ViT), a language model, and a projection layer connecting the two, with representative models including GPT-4V/4o, Claude 3.5, the LLaVA series, and InternVL
80%VerifiedThe project connects to large language models via OpenRouter, which serves as an AI model gateway supporting unified API calls to multiple large models such as GPT-4, Claude, and Llama.
80%VerifiedSince 2024, OpenAI has reduced the API prices of the GPT series multiple times.
80%VerifiedThe Function Calling mechanism was first introduced into the GPT series of models by OpenAI in 2023.
80%Verified当前所有主流大模型（GPT、BERT、LLaMA等）都基于Transformer架构
80%VerifiedGLM采用了独特的自回归填空预训练范式，与GPT的纯自回归和BERT的纯掩码语言模型都有所不同
80%VerifiedThe context windows of current mainstream large language models (such as GPT-4, Claude, etc.) have been expanded to 128K or even longer tokens.
80%VerifiedFunction Calling is a feature first introduced by OpenAI in mid-2023 and subsequently adopted by major model vendors.
80%VerifiedGPT-series models use the Byte Pair Encoding (BPE) algorithm to segment text into tokens.
80%VerifiedIn GPT-series models, one Chinese character typically corresponds to 1 to 2 tokens, and one English word corresponds to approximately 1 to 1.5 tokens.
80%VerifiedThe code generation capabilities of large language models such as GPT-4 and Claude stem from the fact that their training data includes hundreds of millions of open-source code repositories on GitHub.
80%VerifiedCodex is a large language model based on the GPT architecture, fine-tuned specifically for code understanding and generation tasks.
80%