Artificial intelligence (AI) encompasses many complex, emerging technologies that once required human input and can now be performed by a computer. Computers can perform advanced functions, which historically were used to understand and recommend information. Now, with AI, computers can even generate new content.
The acronym AI is often used interchangeably to represent various types of technologies which make up the AI field.
Common AI concepts
There are a number of terms and concepts which define artificial intelligence and machine learning, which you may find useful. Here are some ways you may work with AI in-practice, on the web
General AI
Broadly speaking, general AI is a non-human program or model that demonstrates a broad range of problem solving and creativity. A model is a very large mathematical equation, which includes a set of parameters and structure needed for a machine to return an output.
With general AI, you could perform multiple types of tasks, such as analyzing data, translating text, compose music, identifying diseases, and much more.
Narrow AI
Narrow AI is a system that can perform a singular or specific subset of tasks. For example, a computer that plays a game of chess against a human opponent (not to be confused with the Mechanical Turk). Narrow AI has a predefined set of parameters, constraints, and contexts, which may appear like understanding, but are in fact just answers to an equation.
You may see this in-practice with facial recognition systems, voice assistants, and weather forecasting. You could use highly specific models to improve certain, specific functionality on your web sites and apps.
For example, you built a site dedicated to movies, where users can login, rate their favorite movies and discover new ones to watch. You could use a pre-populated database to recommend movies based on the current page they're visiting. Or, you could use a narrow AI model which analyzes user behavior and preferences to show the most relevant information for that reader.
Generative AI
A large language model (LLM) is a neural network AI model with many parameters that you can use to perform a wide variety of tasks, such as generating, classifying, or summarizing text or images.
Generative AI responds to input and creates content, built on the context and memory of an LLM. This goes beyond pattern matching and predictions. Some of the most common generative AI tools include:
These tools can create written prose, code samples, and images. They can help you plan a vacation, soften or professionalize the tone of an email, or classify different sets of information into categories.
There are endless use cases, for developers and for non-developers.
Client-side, server-side, and hybrid AI
While most AI features on the web rely on servers, client-side AI runs directly in the user's browser. This offers benefits such as low latency, reduced server-side costs, no API key requirements, increased user privacy, and offline access. You can implement client-side AI that works across browsers with JavaScript libraries, including Transformers.js, TensorFlow.js, and MediaPipe.
Server-side AI encompasses cloud-based AI services. Think Gemini 1.5 Pro running on a cloud. These models tend to be much larger and more powerful. This is especially true of large language models.
Hybrid AI refers to any solution including both a client and server component. For example, you could use a client-side model to perform a task and fallback to a server-side model when the task cannot be completed on the device.
It is possible for a small, optimized client-side model to outperform a larger server-side counterpart, especially when optimized for performance. Assess your use case to determine what solution is right for you.
Machine learning (ML)
Machine learning (ML) is a form of AI, where a computer learns without explicit programming. Where AI strives to generate intelligence, ML allows computers to learn from experience. ML consists of algorithms to make predictions of data sets.
ML is the process of training a model to make useful predictions or generate content from data.
For example, suppose we wanted to create a website which rates the weather on any given day. Traditionally, this may be done by one or more meteorologists, who could create a representation of Earth's atmosphere and surface, compute and predict the weather patterns, and determine a rating by comparing the current data to historical context.
Instead, we could give an ML model an enormous amount of weather data, until the model learns the mathematical relationship between weather patterns, historic data, and guidelines on what makes the weather good or bad on any particular day. In fact, we've built this on the web.
Deep learning
Deep learning (DL) is a class of ML algorithms. One example would be Deep Neural Networks (DNNs) which attempt to model the way the human brain is believed to process information.
Challenges with AI
There are several challenges when building and using AI. The following are just a few highlights of what you should consider.
Data quality and recency
Large datasets used to train various AI models are often, inherently out-of-date soon after they're used. This means when seeking the most recent information, you may benefit from prompt engineering to enhance an AI model's performance on specific tasks and produce better outputs.
Datasets can be incomplete or too small to effectively support some use cases. It can be useful to try working with multiple tools or customizing the model to suit your needs.
Concerns with ethics and bias
AI technology is exciting and has a lot of potential. However, ultimately, computers and algorithms are built by humans, trained on data that may be collected by humans, and thus is subject to several challenges. For example, models can learn and amplify human bias and harmful stereotypes, directly impacting the output. It's important to approach building AI technology with bias mitigation as a priority.
There are numerous ethical considerations about copyright of AI-generated content; who owns the output, especially if it's heavily influenced by or directly copied from copyrighted material?
Before generating new content and ideas, consider existing policies on how to use the material you create.
Security and privacy
Many web developers have said that privacy and security are their top concerns in using AI tools. This is especially true in business contexts with strict data requirements, such as governments and healthcare companies. Exposing user data to more third-parties with cloud APIs is a concern. It's important that any data transmission is secure and continuously monitored.
Client-side AI may be the key to address these use cases. There's much more research and development left to do.
Get started with AI on the web
Now that you're familiar with the many types of artificial intelligence, you can start to consider how to use existing models to become more productive and build better websites and web applications.
You could use AI to:
- Build a better autocomplete for your site's search.
- Detect the presence of common objects, such as humans or pets, with a smart camera
- Address comment spam with a natural language model.
- Improve your productivity by enabling autocomplete for your code.
- Create a WYSIWYG writing experience with suggestions for the next word or sentence.
- Provide a human-friendly explanation of a dataset.
- And more...
Pre-trained AI models can be a great way to improve our web sites, web apps, and productivity, without needing a full understanding of how to build the mathematical models and gather complex datasets which power the most popular AI tools.
You may find most models meet your needs right away, without further adjustment. Tuning is the process of taking a model, which has already been trained on a large dataset, and further training to meet your specific usage needs. There are a number of techniques to tune a model:
- Reinforcement learning from Human Feedback (RLHF) is a technique which uses human feedback to improve a model's alignment with human preferences and intentions.
- Low-Rank Adaption (LoRA) is a parameter-efficient method for LLMs which reduces the number of trainable parameters, while maintaining model performance.