Home›Concepts
Concepts
Concepts
How AI works, in plain language: from the artificial neuron to the Transformer, pre-training and reasoning models.
Total 55 · Clear filters
Pre-training and fine-tuningPre-training trains a large model on huge amounts of unlabeled text, and fine-tuning then adapts it to a specific task with a small labeled dataset. This two-stage recipe is the basis of the term foundation model.Retrieval-augmented generationRetrieval-augmented generation (RAG) lets a language model fetch relevant documents from an external store and put them into its prompt before answering, so it can use knowledge beyond its training data and cite where an answer came from.Scaling lawsScaling laws are empirical trends showing that a language model's test loss falls smoothly, as a power law, when parameters, data and training compute grow. They help plan large training runs and explain the race for compute.In-context learningIn-context learning is a large language model's ability to perform a new task from instructions and a few examples placed in the prompt, with no weight updates. Named and studied in the GPT-3 paper, it moved adaptation from fine-tuning to prompt writing.LoRA (low-rank adaptation)LoRA (low-rank adaptation) is a fine-tuning technique that freezes a pre-trained model's weights and trains small low-rank matrices instead, cutting the number of trainable parameters and the memory needed while keeping quality close to full fine-tuning.Instruction tuningInstruction tuning is a supervised fine-tuning stage that trains a large language model to follow user instructions; the FLAN paper showed it substantially improves zero-shot performance on unseen tasks.Chain of thought and reasoning modelsChain of thought is the technique of having a language model write out its intermediate reasoning before answering. Reasoning models extend it by training the model with reinforcement learning to think at length before responding.Speculative decodingSpeculative decoding speeds up text generation from large autoregressive models: a smaller model proposes several tokens and the large model checks them in parallel, producing identical output faster.Constitutional AIConstitutional AI is a training method introduced by Anthropic in December 2022, in which a model's behaviour is shaped by a written constitution of principles rather than by human labels of harmful outputs.Direct preference optimizationDirect preference optimization (DPO) is a method for fine-tuning language models on human preference data with a supervised-learning-style objective, removing the separate reward model and the reinforcement-learning loop of standard RLHF.Text watermarkingText watermarking embeds a hidden statistical signal in generated text so that a short span of tokens can later be identified as machine output, while the text still reads normally to people.Prompt injectionPrompt injection is an attack in which text inside a model's input overrides its original instructions, letting an adversary hijack a language-model application — including, as researchers showed in 2023, through content the application retrieves on its own.Llama Community LicenseThe Meta Llama 3 Community License is the custom agreement Meta attaches to its Llama 3 models: free to use and modify, but with use restrictions, attribution duties and a user-scale threshold that keep it from being open source in the usual sense.Test-time computeTest-time compute is the computation a model spends while answering a prompt, beyond what training already fixed into its weights. A 2024 study by Snell et al. showed how to spend it adaptively, and how it can stand in for a bigger model.Sim-to-real transferSim-to-real transfer is the practice of training robot policies in simulation and then adapting them to physical robots, using synthetic data to supplement costly real-world demonstrations.Reinforcement learningReinforcement learning is the branch of machine learning and optimal control in which an agent learns, by trial and error, which actions in a dynamic environment maximise a reward signal.AI agentAn AI agent is a system that perceives its environment and acts autonomously toward goals. The term covers everything from a thermostat to LLM-driven software that directs its own tool use.Multi-agent systemA multi-agent system is a computing system made of several interacting intelligent agents that coordinate to solve problems too hard for a single agent. Recent frameworks built on large language models let such agents talk to each other.World modelA world model is a machine learning system that learns an internal representation of an environment and predicts how it changes in response to actions, letting agents plan inside a learned simulator instead of by trial and error.Context windowA context window is the full span of text a model can refer to while producing a response, measured in tokens and including the response itself. Its size, and how evenly a model uses it, shape what the model can do.