AI Engineering Quotes

“If we can get people to trust a machine to take us into space, I hope that one day, security measures will be sufficient for us to trust autonomous AI systems.”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models

“RAG, start with simple term-based solutions such as BM25 instead of jumping straight into something that requires vector databases.”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models

“System Prompt and User Prompt Many model APIs give you the option to split a prompt into a system prompt and a user prompt. You can think of the system prompt as the task description and the user prompt as the task.”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models

“Image and Video Production Thanks to its probabilistic nature, AI is great for creative tasks. Some of the most successful AI startups are creative applications, such as Midjourney for image generation, Adobe Firefly for photo editing, and Runway, Pika Labs, and Sora for video generation.”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models

“Other than tools that help with general coding, many tools specialize in certain coding tasks. Here are examples of these tasks: Extracting structured data from web pages and PDFs (AgentGPT) Converting English to code (DB-GPT, SQL Chat, PandasAI) Given a design or a screenshot, generating code that will render into a website that looks like the given image (screenshot-to-code, draw-a-ui) Translating from one programming language or framework to another (GPT-Migrate, AI Code Translator) Writing documentation (Autodoc) Creating tests (PentestGPT) Generating commit messages (AI Commits)”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models

“For example, Amazon Web Services (AWS) has categorized enterprise generative AI use cases into three buckets: customer experience, employee productivity, and process optimization. A 2024 O’Reilly survey categorized the use cases into eight categories: programming, data analysis, customer support, marketing copy, other copy, research, web design, and art. Some organizations, like Deloitte, have categorized use cases by value capture, such as cost reduction, process efficiency, growth, and accelerating innovation.”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models

“AI engineering refers to the process of building applications on top of foundation models.”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models

“Using a database to supplement the instructions is called retrieval-augmented generation (RAG). You can also finetune—further train—the model on a dataset of high-quality product descriptions. Prompt engineering, RAG, and finetuning are three very common AI engineering techniques that you can use to adapt a model to your needs.”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models

“In AI, there are generally three types of competitive advantages: technology, data, and distribution—the ability to bring your product in front of users. With foundation models, the core technologies of most companies will be similar. The distribution advantage likely belongs to big companies.”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models

“Here are a few examples of different levels of risks, ordered from high to low: If you don’t do this, competitors with AI can make you obsolete. If AI poses a major existential threat to your business, incorporating AI must have the highest priority. In the 2023 Gartner study, 7% cited business continuity as their reason for embracing AI. This is more common for businesses involving document processing and information aggregation, such as financial analysis, insurance, and data processing. This is also common for creative work such as advertising, web design, and image production. You can refer to the 2023 OpenAI study, “GPTs are GPTs” (Eloundou et al., 2023), to see how industries rank in their exposure to AI. If you don’t do this, you’ll miss opportunities to boost profits and productivity. Most companies embrace AI for the opportunities it brings. AI can help in most, if not all, business operations. AI can make user acquisition cheaper by crafting more effective copywrites, product descriptions, and promotional visual content. AI can increase user retention by improving customer support and customizing user experience. AI can also help with sales lead generation, internal communication, market research, and competitor tracking. You’re unsure where AI will fit into your business yet, but you don’t want to be left behind. While a company shouldn’t chase every hype train, many have failed by waiting too long to take the leap (cue Kodak, Blockbuster, and BlackBerry). Investing resources into understanding how a new, transformational technology can impact your business isn’t a bad idea if you can afford it. At bigger companies, this can be part of the R&D department.”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models

“Before investing time, money, and resources into building an application, it’s important to understand how this application will be evaluated. I call this approach evaluation-driven development.”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models

“evaluation-driven development.”
― Chip Huyen, AI Engineering: Building Applications with Foundation Models