Large Language Model
Core Facts
The core idea of RAG is to retrieve relevant information from an external knowledge base as context to inject into the prompt before the large model generates a response.
'Hallucination' refers to large language models generating plausible-sounding but factually incorrect content with high confidence
Mainstream Agent architectures typically use a large language model as the brain, combined with memory modules, planning modules, and tool interfaces to accomplish complex tasks
Timeline (last 90 days)
The hallucination problem cannot be eradicated by increasing the number of parameters or switching to better corpora, because the probabilistic generation paradigm itself determines that deviations are inevitable.
The tendency of large language models to hallucinate is one of the most realistic risks in AI website building; models will fabricate names, job titles, reviews, numbers, qualifications, awards, certifications and other content in order to ensure the output 'looks complete and coherent.'
Ordinary large model products (such as Doubao) can analyze problems and generate solutions, but cannot enter the user's computer environment, and cannot access local files, call software, or execute commands.
AI agents based on large language models already have the ability to browse e-commerce websites, compare prices, place orders, and even complete payments.
Large language models have already surpassed humans in frontier mathematics and programming.
当前主流大语言模型都存在上下文窗口限制（如128K tokens），AI在生成长应用时无法同时看到全部代码，导致跨会话生成的模块接口漂移。
The length of text a large model can "see" at each inference is limited, and this stretch of text is called the context window
The options in interactive answers are dynamically generated in real time by the large language model based on the current conversation context, rather than being pre-defined by humans.
A single model itself has no persistent goals, but once connected to tool calling, memory and a looped decision-making framework, it exhibits clear agentic characteristics.
Large language models themselves are stateless, and each request is an independent computation; so-called 'remembering' usually relies on two mechanisms: one is concatenating historical conversation into the current prompt (the context window), and the other is retrieval-augmented generation (RAG) through external storage (such as vector databases or file systems).
40 more timeline events
All Facts (20)
The core idea of RAG is to retrieve relevant information from an external knowledge base as context to inject into the prompt before the large model generates a response.
90%Verified'Hallucination' refers to large language models generating plausible-sounding but factually incorrect content with high confidence
90%VerifiedMainstream Agent architectures typically use a large language model as the brain, combined with memory modules, planning modules, and tool interfaces to accomplish complex tasks
90%VerifiedReasoning models perform better in information synthesis tasks requiring multi-step logical deduction, but have higher latency and should be selected appropriately based on task characteristics.
90%VerifiedFunction Calling (Tool Use) is a standardized mechanism for large models to invoke external tools, where developers pre-declare tool names, descriptions, and parameter schemas, and the model autonomously determines when to make a call.
90%VerifiedAgents possess capabilities for planning, tool invocation, memory, and autonomous iteration, distinguishing them from the single-round question-and-answer mode of traditional large language models.
90%VerifiedThe context window of a large language model determines the upper limit of information the model can process in a single inference.
90%VerifiedPrompt注入（Prompt Injection）是针对大语言模型应用的安全威胁，攻击者通过在输入中嵌入恶意指令试图覆盖系统原有行为约束
90%VerifiedTest-time Compute Scaling improves model performance by investing more computational resources during the inference stage, and research indicates it is more efficient than simply increasing model parameter count on certain tasks.
90%Verified训练一个顶级大模型的成本已达数亿美元级别
90%VerifiedModern large language models typically go through three training stages: pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF).
90%VerifiedThe root cause of AI hallucination lies in the generative mechanism of LLMs: the model is essentially performing next-token probability prediction, optimizing for linguistic coherence rather than factual accuracy.
90%VerifiedLarge language models are based on the Transformer architecture and are trained on massive amounts of text data.
90%VerifiedLLMs exhibit a 'Lost in the Middle' phenomenon, where the model pays more attention to information at the beginning and end of the context while tending to overlook information in the middle.
90%VerifiedSince 2023, with the improvement in large language model capabilities, AI agents have rapidly moved from an academic concept to actual product deployment.
90%VerifiedThe pre-training process of large language models requires thousands of high-end GPUs running in parallel for months, with costs typically ranging from tens of millions to hundreds of millions of dollars.
90%VerifiedAI programming assistance tools such as GitHub Copilot, Cursor, and Claude are essentially code completion and generation systems formed by training large language models on massive code repositories.
90%VerifiedA new generation of AI code generation tools can decompose natural language requirements into complete engineering tasks, autonomously select the technology stack, generate file structures, and complete the debugging loop.
90%VerifiedToken是大语言模型处理文本的基本单位，大约对应0.75个英文单词或1.5个汉字
90%VerifiedThe computational cost of large language models depends primarily on the number of tokens, model parameter scale, and context window size.
85%