Adaptability
Adaptability is the capacity of a system or agent to adjust its behavior, methods, or configuration in response to changing conditions, information, or feedback.
Generative AI in Action
Model adaptation is the adjustment of a generative AI model so that its outputs perform better for particular tasks or domains.
- How it is used
- Tailors pretrained language models to specialized enterprise tasks and domains.
- How deep it goes
- Explains adaptation categories, parameter-update approaches, and selection trade-offs without mathematical derivation.
- Examples
- Uses medical questions, medical news, sentiment analysis, and emotion detection to distinguish domain from task adaptation.
- What you can do after
- Evaluate/understand when to adapt a model and which fine-tuning approach merits testing against a defined use case.
Deep Learning with R, Third Edition
Adaptability is the ability of a system or agent to adjust its behavior in response to unexpected conditions or new information.
- How it is used
- Contrasts intelligence with automation and evaluates how systems respond beyond trained or programmed situations.
- How deep it goes
- Defines adaptability conceptually and illustrates failure on novelty, but does not provide mechanisms for building adaptive systems.
- Examples
- Uses a leopard-print sofa classification error, memorized LLM programs, and a novel puzzle to demonstrate failure beyond training data.
- What you can do after
- Evaluate whether a system retrieves familiar patterns or adapts when faced with situations outside its training distribution.
Read how Deep Learning with R, Third Edition explains adaptability →
The Art of AI Product Development
Adaptability is the capability of a system to detect changing conditions and adjust its behavior in response to them.
- How it is used
- Positions adaptability as a capability of autonomous enterprises operating within changing business environments.
- How deep it goes
- Explains sensing, foresight, monitoring, desirability assessment, and response, but stops short of implementation details.
- Examples
- Uses competitor product updates, desirability estimates, success monitoring, and feature suggestions as concrete examples.
- What you can do after
- Evaluate adaptive behavior by tracing how environmental signals become monitored, strategically aligned feature suggestions.
Read how The Art of AI Product Development explains adaptability →
Effective Conversational AI
Adaptiveness is the ability of a conversational system to adjust its response to the user's wording, tone, context, or requested level of detail.
- How it is used
- Adjusts conversational responses to user context, wording, tone, and requested detail.
- How deep it goes
- Explains contextual localization and response-style adjustment through a worked chatbot comparison.
- Examples
- Uses PharmaBot’s New York restaurant-guideline question and contrasts generic intent-based and localized RAG responses.
- What you can do after
- Apply it via retrieval-augmented generation to produce more relevant, localized, and stylistically appropriate answers.
Read how Effective Conversational AI explains adaptability →
The Creative Programmer
The capacity to adjust behavior, methods, or knowledge to changing situations and requirements.
- How it is used
- Uses adaptability to connect generalist experience with better responses to changing situations and constraints.
- How deep it goes
- Defines adaptability through related generalist advantages but stops short of offering a step-by-step practice.
- Examples
- Uses career changes, a beginner’s-mind quotation, and novice game developers working against expert assumptions.
- What you can do after
- Apply it by changing approaches across situations and remaining open to possibilities that expertise may overlook.
Related concepts
- low-rank adaptationincludes · Low-rank adaptation is a parameter-efficient fine-tuning method that adapts a model by learning low-rank updates to its weights, typically while keeping most original weights fixed.
- fine-tuningincludes · Fine-tuning is adapting a pretrained machine-learning model by training it further on targeted data or objectives for a task, domain, or behavior.
- retrieval-augmented generationproduced by · Retrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
- language modelcontrasts with · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
- foundational modelused by · A base or foundation model is a pretrained model that provides learned parameters or capabilities as a starting point for reuse or adaptation to downstream tasks.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.