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 Transformer architecture replaced the recurrent structure of RNNs, greatly improving training efficiency, and is the underlying backbone of modern large language models such as GPT and BERT.
Mistral AI takes "open + efficient" as its differentiated route, has accumulated a high reputation in the open-source community, and the Large series plays the role of competing head-on with frontier closed-source models such as GPT and Claude.
Gemini 4 Argon can directly listen to a beat and write lyrics, whereas GPT and Claude can only analyze numerical values such as BPM.
The same Claude or GPT model can be driven to different behaviors by different harnesses such as Claude Code and OpenCode.
Under the hood, Hermes actually calls complex reasoning models, such as the GPT series, the Claude series, or some open-weight model.
For the same simple request, a reasoning model (such as Claude or GPT) typically takes 2 seconds or even 5 seconds to complete the entire chain.
Naming the authoritative output improves the three GPT models by 6.3 to 7.9 percentage points over ordinary retrieval.
After re-running all 11,007 logged simulator calls, it was found that the two GPT models computed the key values about as frequently as before.
Under the retrieval condition, the GPT models often skip the report, answer based on their own higher-precision output files, and incorrectly round to an adjacent option, a failure mode the researchers call "evidence substitution".
The rubber duck agent built into Copilot CLI uses GPT to review plans written by Opus, leveraging differences in the training data of different models for cross-validation.
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%VerifiedVibe Coding是指开发者以自然语言描述意图、由AI完成大部分代码生成的编程范式
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%