--- title: AI Basics: Five Interview Questions, Answered | daily.dev description: A primer on five common AI interview questions aimed at data professionals: distinguishing AI, machine learning, deep learning and generative AI as nested... canonical: https://daily.dev/posts/ai-basics-five-interview-questions-answered-dxw5qjwvz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: AI Basics: Five Interview Questions, Answered | daily.dev og:description: A primer on five common AI interview questions aimed at data professionals: distinguishing AI, machine learning, deep learning and generative AI as nested... og:url: https://daily.dev/posts/ai-basics-five-interview-questions-answered-dxw5qjwvz og:image: https://api.daily.dev/og/posts/DXw5qjWvz.png og:image:alt: AI Basics: Five Interview Questions, Answered og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # AI Basics: Five Interview Questions, Answered **[SQL Authority](https://daily.dev/sources/sql-authority)** · 4 min read · 1 upvotes · 0 comments ## Summary A primer on five common AI interview questions aimed at data professionals: distinguishing AI, machine learning, deep learning and generative AI as nested circles; defining large language models as next-token predictors; contrasting training with inference and their cost implications; explaining knowledge cutoffs and their practical effects on data work (stale advice about deprecated features or missing versions); and clarifying that models don't learn during a conversation, separating the live model, app memory features, and vendor data policies. Includes a five-minute exercise to test an assistant's knowledge cutoff against a database product's latest version, and promotes a companion book with 100 interview questions across ten chapters. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the difference between training and inference for a large language model? Training is when the model learns from data, an expensive upfront process; inference is when the finished model is used, producing an answer from a prompt. Every time someone sends a prompt to a deployed model, that's inference, and it's the recurring cost behind usage bills, not training. Using a model does not retrain it or change its parameters. _Developers weighing LLM usage costs can track explainers like this on daily.dev._ ### What is a knowledge cutoff in a large language model and why does it matter for using a database? A knowledge cutoff is the date a model's training data ends; ask about anything newer and it either admits ignorance or guesses, often confidently and incorrectly. For data work this surfaces as outdated advice: recommending a deprecated feature, missing a newly added function, or naming an old version as the latest. The model has no built-in sense of today's date, so wrong answers can sound current. The vendor publishes the actual cutoff date; asking the model itself is unreliable. _Anyone vetting an AI assistant's database advice can follow coverage like this on daily.dev._ ### Does a large language model learn from my conversation while I'm chatting with it? No, the model's parameters do not change during a conversation; it is not learning in real time. Some products add a separate memory feature that saves notes from the chat and feeds them back later, but that is the application storing text, not the model learning. The vendor may still log, keep, or use the conversation to train a future model version depending on its data policy and settings. _Teams deciding what data is safe to paste into an AI tool can follow guidance like this on daily.dev._ ## Similar posts on daily.dev - [100 AI Interview Questions and Answers: New Book](https://daily.dev/posts/100-ai-interview-questions-and-answers-new-book-zni8txmmm) · SQL Authority · 1 upvotes · 0 comments - [Artifical Intelligence — Prep Interview](https://daily.dev/posts/artifical-intelligence-prep-interview-oxsaumswp) · Medium · 1 upvotes · 0 comments - [Artificial Intelligence, Machine Learning, Deep Learning, and Generative AI — Clearly Explained](https://daily.dev/posts/artificial-intelligence-machine-learning-deep-learning-and-generative-ai-clearly-explained-jwnfhvd2r) · Towards Data Science · 1 upvotes · 0 comments - [What AI Engineer Interviews Really Test: A Practical Guide to Preparing for Modern AI Roles](https://daily.dev/posts/what-ai-engineer-interviews-really-test-a-practical-guide-to-preparing-for-modern-ai-roles-r5libav3b) · SitePoint · 1 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#llm](https://daily.dev/tags/llm), [#genai](https://daily.dev/tags/genai), [#interview-questions](https://daily.dev/tags/interview-questions) [View this post on daily.dev](https://daily.dev/posts/ai-basics-five-interview-questions-answered-dxw5qjwvz) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"AI Basics: Five Interview Questions, Answered","url":"https://daily.dev/posts/ai-basics-five-interview-questions-answered-dxw5qjwvz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ai-basics-five-interview-questions-answered-dxw5qjwvz"},"datePublished":"2026-10-01T03:23:52.218Z","dateModified":"2026-10-01T03:24:16.469Z","description":"A primer on five common AI interview questions aimed at data professionals: distinguishing AI, machine learning, deep learning and generative AI as nested...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/5995d30f9c9c600a194f1aa73b89c63d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/5995d30f9c9c600a194f1aa73b89c63d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"SQL Authority","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"SQL Authority","logo":"https://media.daily.dev/image/upload/s--reCGnvgi--/f_auto,q_auto/v1780213436/logos/sql-authority?_a=BAMAMiWQ0","url":"https://daily.dev/sources/sql-authority"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ai-basics-five-interview-questions-answered-dxw5qjwvz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,llm,genai,interview-questions","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"SQL Authority","item":"https://daily.dev/sources/sql-authority"},{"@type":"ListItem","position":3,"name":"AI Basics: Five Interview Questions, Answered"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/ai-basics-five-interview-questions-answered-dxw5qjwvz#faq","mainEntity":[{"@type":"Question","name":"What is the difference between training and inference for a large language model?","acceptedAnswer":{"@type":"Answer","text":"Training is when the model learns from data, an expensive upfront process; inference is when the finished model is used, producing an answer from a prompt. Every time someone sends a prompt to a deployed model, that's inference, and it's the recurring cost behind usage bills, not training. Using a model does not retrain it or change its parameters. Developers weighing LLM usage costs can track explainers like this on daily.dev."}},{"@type":"Question","name":"What is a knowledge cutoff in a large language model and why does it matter for using a database?","acceptedAnswer":{"@type":"Answer","text":"A knowledge cutoff is the date a model's training data ends; ask about anything newer and it either admits ignorance or guesses, often confidently and incorrectly. For data work this surfaces as outdated advice: recommending a deprecated feature, missing a newly added function, or naming an old version as the latest. The model has no built-in sense of today's date, so wrong answers can sound current. The vendor publishes the actual cutoff date; asking the model itself is unreliable. Anyone vetting an AI assistant's database advice can follow coverage like this on daily.dev."}},{"@type":"Question","name":"Does a large language model learn from my conversation while I'm chatting with it?","acceptedAnswer":{"@type":"Answer","text":"No, the model's parameters do not change during a conversation; it is not learning in real time. Some products add a separate memory feature that saves notes from the chat and feeds them back later, but that is the application storing text, not the model learning. The vendor may still log, keep, or use the conversation to train a future model version depending on its data policy and settings. Teams deciding what data is safe to paste into an AI tool can follow guidance like this on daily.dev."}}]} ```