Using Generative AI To Do Research

These tools are typically associated with the capability of generating new written content in response to prompts. They are transformers because they work with enormous amounts of text and other data and employ algorithms to find patterns in the datasets they are trained on (mainly from internet sources). They are commonly referred to as Large Language Models (LLMs) using probability or predictive technology to determine which words should appear in a sequence in response to prompting. 

Examples of these tools include: ChatGPT (OpenAI), Google (Gemini), Co-Pilot (Microsoft), Claude (Anthropic), DeepSeek (DeepSeek), and Perplexity (Perplexity AI). Consult this guide on Microsoft Copilot from York's University Information Technology Department to learn how best to get access to this tool if you are a York community member, including the Enterprise data protection feature which means your privacy is better protected than free versions of other tools like ChatGPT (OpenAI).

What these tools produce in textual form can take many forms, e.g., summaries, reflective statements, blogs, poetry and more. Features will vary for different versions and/or for free versus pro models. Increasingly these tools are multi-modal with the capacity to generate images, code and more.

Image generators create images from textual descriptions and/or from other images. They work with huge datasets of images and generate outputs based on analysis of those images, including their captions and text descriptions. 

Popular image generators include DALL-E (OpenAI), AI Image Generator (FreePik), Leonardo (Leonardo.AI), Flux.1 (Flux.AI) ImageFX (Google), Midjourney (Midjourney AI), Stable Diffusion (Stability AI), Runway (Runway AI), Adobe Firefly (Adobe), Ideogram (Ideogram AI) and Recraft (Recraft.AI). Many of the AI tools you likely already know like ChatGPT (OpenAI), Gemini (Google), and Co-Pilot (Microsoft) now include image creation features tools with some functions even available in their free versions. 

The results can take many forms, e.g., graphics or media, including cartoons, photos, anime, oil paintings, illustrations and more. 

Audio generators are designed for audio generation or processing tasks. They are often broken down in to different sub-types including those that facilitate voice generation/cloning and those that generate music or sound effects. Prompts might take the form of text, musical notes, melodies or chord progressions, or audio samples or excerpts. They train on audio data and through this process they can generate new audio that has the style and characteristics of the data they were trained on. 

Examples include Suno-ai, Udio, AIVA, Boomy, Soundraw, ElevenLabs, Soundful, Lovo, Murf.ai and Speechify.

What they produce may take the form of synthesized voices, sound effects, background soundscapes, and music in the form of songs, melodies, compositions, etc. This can even include new genres of music that mimic existing styles. 

Video generators create video content. Prompts can be given in various forms, including text, images, or videos. They are trained on large datasets of video clips, including movies, TV shows, or other video content. Using this data, they are trained to understand and replicate visual patterns and structures in the input video data, as well as temporal and spatial features. Just as with audio tools, these tools can now often assist with video editing and are starting to appear in tools like Adobe Premiere or DaVinci Resolve. 

Examples include Sora (OpenAI), Veo (Google DeepMind), Dream Machine (LumaLabs), HeyGen,  Kling AI, Runway, Pika, Synthesia, AI Studios (Deepbrain AI), Invideo, and Deforum.

What they produce can take many forms, ranging from generating simple animations or special effects to complex video scenes or entire movies. 

Research Discovery and workflow tools cover quite a range of tools. They work with scholarly research outputs like articles to search and analyze them, extract key information, generate literature reviews, maps and summaries, or provide features common with citation tools. In a nutshell, they are often billed as helping to automate research workflows.

Examples include Elicit, Scite, ResearchRabbit, and Semantic Scholar. 

These tools are much more fully explored in the Research Discovery & Workflow Tools section of this guide. Quite a number of these tools are not 100% free and require a subscription for full functionality and have usage limits.

Coding tools write code, i.e. they function as code generators or coding assistants. Examples of features include code generation, code behaviour analysis, code review, bug detection, code auto-documentation etc.

Some of the best known tools include GitHub Copilot, Cursor, Aider, Windsurf, SourceAI, Tabnine, Qodo, Replit,  Amazon Q Developer and Phind.

Many of the AI tools you likely already know like ChatGPT (OpenAI), Gemini (Google), and Claude (Anthropic) now incorporate code-generation features too, with some aspects of this even available in the free versions.