Home›Concepts
Concepts
Concepts
How AI works, in plain language: from the artificial neuron to the Transformer, pre-training and reasoning models.
Total 40 · Clear filters
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.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.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.Long contextLong context is a model's capacity to take in and work over very large inputs — documents, images, recordings — in a single request. Systems now reach millions of tokens, though finding information inside that window is a separate skill.QuantizationQuantization stores a language model's weights and activations at lower numerical precision, cutting the memory and bandwidth that inference requires. Methods such as LLM.int8() and GPTQ made very large models runnable on far smaller hardware.KV cacheA KV cache keeps the key and value vectors a model has already computed for earlier tokens, so each new token reuses them instead of recomputing. Its memory footprint is what makes high-throughput serving hard to scale.Prompt engineeringPrompt engineering is the practice of designing the text input that steers a generative AI system toward a desired output. Shared vocabulary and techniques such as chain-of-thought prompting make results easier to describe, compare and reproduce.Synthetic dataSynthetic data is training material written by a model rather than collected from people or the web. In the phi-1 experiments a small code model trained partly on model-generated "textbooks" reached competitive benchmark scores, suggesting data quality itself shapes capability.Tool callingTool calling lets a language model hand a sub-task, such as arithmetic or search, to an external program and use the result in its answer. Toolformer showed in 2023 that a model could learn when and how to call tools on its own.Planning in AI agentsPlanning in AI agents is the process of breaking a goal into intermediate steps, choosing actions, and revising the plan as results arrive, rather than producing an answer in one pass.[^1][^2]Agent memoryAgent memory is the part of an agent system that stores information beyond the current context window so it can be recalled later. MemGPT (2023) framed the limited context window as the core constraint such designs must work around.HallucinationHallucination is false or misleading information that a model presents as fact. It is a central failure mode of text-generating systems and a main obstacle to trusting their output.Benchmark contaminationBenchmark contamination means the test items a model is evaluated on, or close variants of them, were present in its pretraining data, so scores partly measure memory of seen text rather than the ability the benchmark is meant to probe.Red teamingRed teaming is the practice of actively probing a model for harmful or unwanted behaviour before deployment. A 2022 method by Perez and colleagues automated it by using one language model to generate test cases for another.AI alignmentAlignment is the problem of making a model's behaviour match what its users and designers actually intend, not just what its training objective literally rewards. Training on human preference comparisons is one practical route to it.JailbreakA jailbreak is an adversarial prompt that gets a safety-trained model to produce behaviour its training was meant to prevent. A 2023 analysis by Wei et al. traced these failures to competing objectives and mismatched generalization.