Utilizing GenAI tools effectively involves choosing the right tool for the task at hand, crafting prompts that generate the output you want/expect, AND using the tools ethically and with integrity. While this section of the guide focuses on crafting prompts and evaluating and choosing specific tools,
Learn Prompting defines "prompt engineering" as "the process of communicating effectively with an AI to achieve desired results."
Using GenAI tools effectively requires that the user know the right questions to ask, and how to phrase them for the best results. Vague or generic questions generate vague or generic results. (In other words, garbage in, garbage out.)
Tips for crafting prompts to get the best results from chatbots:
The definitive guide to prompt engineering. Extensive but easy-to-read online guide to crafting prompts. Each chapter is only a few paragraphs and includes illustrations and hands-on examples. Great as a reference - does not need to be read all at once or sequentially.
Thorough overview with examples of different types of prompts. Serves as a good one-page cheatsheet to Learn Prompting.
OpenAI's guide to strategies and tactics for getting better results from GPTs offers six strategies for getting better results
Quick Guide: AI Prompt Engineering infographic (by Jeri Hurd, Branksome Hall Asia)
Get the Best From ChatGPT With These Golden Prompts (The New York Times: On Tech: A.I.)
Generative AI Is Only as Good as the Prompt You Give It (Inside Higher Ed, 4/26/2023)
Collection of pre-written prompts.
Generates a ChatGPT prompt based on choices in dropdown menus.
Many tech reviewers have published comparisons between popular AI chatbots, but the landscape changes rapidly.
This guide primarily features free and freemium tools. We recommend experimenting with these options before investing in any paid subscriptions. Unless you need a feature that is unique to another tool, we also highly recommend choosing chatbots that connect to the internet and provide links so that you can verify their claims.
Chatbot powered by Microsoft's proprietary Prometheus, which combines GPT-4 (which also powers the subscription version of ChatGPT) and Bing web search. Copilot's Designer is powered by DALL-E 3. Copilot can help users with a variety of tasks, such as writing code, generating text, creating graphic art from text descriptions, and finding information on the web. As of early 2024, Copilot is considered the best free alternative to a paid ChatGPT subscription.
Enhance online research with Copilot’s AI-powered search features (Microsoft Guide)
Art and creative writing Copilot AI showcase (Microsoft Guide)
Microsoft Copilot "secret" prompt generator for Microsoft Edge
Copilot Cheat Sheet (Formerly Bing Chat): Complete Guide for 2024 (Tech Republic, 1/25/2024)
Perplexity AI is an AI-powered search engine and chatbot that is designed to provide accurate and comprehensive answers to user queries. By searching the web in real-time, it offers up-to-date information on a wide range of topics. It is particularly notable as the only chatbot with an "Academic" Focus setting.
Getting Started: What you need to know to get started with Perplexity
ChatGPT is OpenAI's best-in-class generative AI chatbot. Free-tier users can have conversations, gain insights into text or data, and automate tasks. ChatGPT itself does not have internet access and may hallucinate citations and links, but free users now have access to custom GPTs--tools created for specific tasks, including searching the internet or scholarly sources.
Discover custom versions of ChatGPT that combine instructions, extra knowledge, and any combination of skills.
Claude is an "AI assistant created by Anthropic to be helpful, harmless, and honest." Claude is known for having a particularly large memory and can summarize large documents or multiple pdfs. Claude currently cannot search the internet or provide links to its sources.
How to start a conversation and edit prompts.
Google's Gemini Advanced: Tasting Notes and Implications (One Useful Thing, 2/8/2024)
Meta's popular, open source Llama model powers many different tools. Meta AI's assistant is available as a stand-alone app and infused throughout Meta's products like Facebook and Instagram. The assistant in Facebook, Instagram, and WhatsApp messengers is designed to provide personalized and empathetic responses, understand context and nuances of human conversations, and offer creative solutions and ideas.
Poe by Quora is a unique platform that gives users access to multiple AI chatbots in one place. Includes its own GPT-3.5-turbo assistant, Claude, GPTs, LLaMa and Code LLaMa, and Gemini, Gemma, and PaLM, Mistral, Mixtral, and large collection of other models. Also includes a variety of specialized bots and image generators, including StableDiffusionXL and Playground.
Groq is a powerful AI chatbot that utilizes an LPU Inference Engine and is known for its speedy responses. Utilizes Gemma, Llama, and Mixtral models.
Try new and popular open source models hosted on Hugging Face
Try an ever-growing variety of open source models hosted by Perplexity
GitHub repo of featuring curated list of papers about large language models, frameworks for LLM training, tools to deploy LLM, courses and tutorials about LLM and all publicly available LLM checkpoints and APIs:
Created by researchers at UC San Diego and UC Berkeley, Chatbot Arena is a benchmark platform for large language models (LLMs) that features anonymous, randomized battles in a crowdsourced manner.
The Open LLM Leaderboard aims to track, rank and evaluate LLMs and chatbots as they are released. Anyone from the community can submit a model for automated evaluation on the GPU cluster.
If you are working on a project that requires citations, you want to confirm the generative AI chatbot's information sources, or you are seeking information newer than would be included in the chatbot's large language model (LLM), you will want to use a generative AI tool with internet search capabilities like Microsoft Copilot (Bing Chat) or Google SGE (Search Generative Experience).
Perplexity AI is an AI-powered search engine and chatbot that is designed to provide accurate and comprehensive answers to user queries. By searching the web in real-time, it offers up-to-date information on a wide range of topics. It is particularly notable as the only chatbot with an "Academic" Focus setting.
Chatbot powered by Microsoft's proprietary Prometheus, which combines GPT-4 (which also powers the subscription version of ChatGPT) and Bing web search. Copilot's Designer is powered by DALL-E 3. Copilot can help users with a variety of tasks, such as writing code, generating text, creating graphic art from text descriptions, and finding information on the web. As of early 2024, Copilot is considered the best free alternative to a paid ChatGPT subscription.
Google Search Generative Experience (SGE) is an AI-driven feature that generates interactive AI snippets to provide users with accurate and relevant answers to their queries, along with links to corroborating sources AI generated summary. Also provides the standard Google search results links below the AI summary. Join the waitlist in Google Labs.
"AI chatbot to search the web"
Ask a research question to find article citations and then extract key features like main findings or methodology into a comparison table. Chat with papers and extract data from uploaded PDFs. Utilizes the Semantic Scholar articles dataset.
Consensus is a search engine that uses AI to extract and distill findings from peer-reviewed sources. Subject matter coverage ranges from medical research and physics to social sciences and economics. Utilizes the Semantic Scholar dataset.
Provide a seed article that allows you to retrieve recommended papers, visualize networks of papers and authors, and get alerts about additional relevant research. It integrates with Zotero and allows for collaborative research sharing.
A project at the Allen Institute for AI, it indexes over 200 million academic papers sourced from publisher partnerships, data providers, and web crawls.
Don’t Use A.I. to Cheat in School. It’s Better for Studying.(New York Times On Tech: AI)
Claude is an "AI assistant created by Anthropic to be helpful, harmless, and honest." Claude is known for having a particularly large memory and can summarize large documents or multiple pdfs. Claude currently cannot search the internet or provide links to its sources.
"Chat with any PDF"
Docalysis is an AI tool that allows you to chat with your PDF files and get answers to your questions within seconds.
"Upload a paper, highlight confusing text, get an explanation."
Generate ChatGPT summaries of YouTube video transcripts. Extension for Chrome and Safari.
Create notebooks of up to 20 sources including text, Google Docs, and pdfs and then ask them questions. Requires a personal Google account and activation via Google Labs.
"ChatGPT for all your files"
Examples of prompts to improve your outline, vocabulary, grammar, and overall essay.
Embedded in Microsoft Edge browser in Copilot settings. May not be available for enterprise accounts.
Powered by OpenAI's GPT-3. Free tier only offers a one-time allotment of 25 Magic Write generated documents.
Embedded in Google Workspace apps such as Google Docs and Gmail. Users with personal accounts can apply to join the tester program in Google Labs.
Google Workspace Labs is a trusted tester program for personal account users to try new AI features. Activates features in Google Docs, Gmail, Google Slides, Google Sheets, Google Meet, Google Drive, Keep
How use use Help Me Write in Google Docs and Gmail; Help Me Organize in Google Sheets; and image creation in Google Slides.
Other AI-powered tools to improve your writing. Students take note: please make sure that you are using these in accordance with your instructor's rules on use of generative AI. If you have questions or concerns, please consult your instructor first.
"Type or paste text to see ideas for improvement." DeepL Write is an AI-powered writing companion that can help you write clearly, precisely, and with ease in English or German.
"It's like a spellchecker, but for style." Hemingway Editor is a writing app that helps you improve your writing by highlighting and suggesting corrections for common issues, such as long sentences, passive voice, and grammar errors.
"Work with an AI writing partner that helps you find the words you need"
QuillBot was created as a full-sentence thesaurus to help students and professionals write more confidently and quickly.
Wordtune is an AI-powered writing tool that helps you write better and faster by suggesting alternative ways to express your ideas, tone, and voice.
Most AI image generating sites operate on a freemium model where users are allotted a set number of credits. For many tools, the credits reset daily or monthly, but some tools provide only a one-time allotment. Users who pay for accounts can generally unlock more credits and/or premium features. We do not recommend paying for any sites without further research.
University of Arizona Libraries tutorial: Creating multimedia with AI tools
How to Use A.I. to Edit and Generate Stunning Photos (The New York Times: On Tech: A.I.)
How to Write AI Art Prompts [Examples + Templates] (HootSuite, 7/5/2023)
DALL-E is OpenAI's text-to-image model. DALL-E 3 is included in a ChatGPT Plus subscription or available for free via Copilot Design.
Text-to-image generator powered by OpenAI's DALL·E 3. Free with a Microsoft account. Bing suggests the following template to get started: adjective + noun + verb + image/art style. Also see Image prompting 101 (Microsoft Guide)
OpenAI's freemium text-to-image generator. No longer free for new subscribers. Copilot Designer / Bing Image Creator is a free alternative.
FLUX.1 is a suite of advanced text-to-image models known for their exceptional image detail, prompt adherence, style diversity, and scene complexity. FLUX is developed by Black Forest Labs, which was founded by former researchers from Stability AI.
Flux on Freepik is fully integrated and user-friendly, making high-quality image generation accessible to everyone, from beginners to seasoned professionals. Free users will automatically have access to Flux Fast, while Premium users can choose between the advanced capabilities of Flux and Flux Realism.
Stable Diffusion is a family of popular open source text-to-image models created by Stability AI. Anyone can download and run the code on their own PC, and a plethora of generative AI sites have incorporated Stable Diffusion code into their tools in both its original form and modified through low-ranking adaptation (LoRA), an AI training technique that helps to fine-tune the models.
Robust tool that bills itself as a free alternative to Midjourney. Includes an assortment of both general and finely-tuned Leonardo, Stable Diffusion, and member-created models, each crafted for different types of content generation. Free users have a daily allowance of 150 Tokens. How to Write Great Text-to-Image Prompts
Mage.Space AI is an AI art generator that offers several Stable Diffusion models and various features like text-to-image, image-to-image, and image-to-GIF conversions. The tool has a slightly complex interface, but it offers various image creation and editing features. The free plan includes Unlimited creations with SDXL, Stable Diffusion v1.5, or Stable Diffusion v2.1. Paid plans unlock additional models.
NightCafe bills itself as an AI Art Generator with a focus on community and fun. Features SDXL, SD1.5, and other models plus a large collection of community fine-tuned models. Users can log in and collect 5 free credits per day. Users can also participate in AI Art Challenges and interact with a community of other AI Art enthusiasts.
Playground AI is another popular and user-friendly site for generating images with Stable Diffusion XL (SDXL) and Playground's own models. Users can generate 100 free images per day.
Dezgo is a free site where users can generate an image from a text description, powered by Stable Diffusion models. You can use the free version without registering but there are limitations such as rate limits, image resolution and image quality (capped sampling steps).
Civitai is a free, open-source, generative AI platform that allows users to share and use AI image-generating models.
Site where users can share and use AI image-generating models, similar to Civitai. Users can generate 100 free images per day.
Poe by Quora is a unique platform that gives users access to multiple AI chatbots in one place. Includes its own GPT-3.5-turbo assistant, Claude, GPTs, LLaMa and Code LLaMa, and Gemini, Gemma, and PaLM, Mistral, Mixtral, and large collection of other models. Also includes a variety of specialized bots and image generators, including StableDiffusionXL and Playground.
Lexica is an image generation tool that utilizes Stable Diffusion 1.5 and Lexica's own Aperture models. Also includes a search engine to search images that have already been generated.
Despite its name, Stable Diffusion Online is not associated with StabilityAI and some users have raised questions about the site, especially its paid version. Has a nice interface for choosing artistic style. 10 free credits reset daily.
Powered by Stable Diffusion. Free Canva users have 50 lifetime credits, while Canva Pro members have 500 credits per month.
Canva tool to automatically generate templates based on uploaded image or entered text prompt. Canva can also generate a 10-slide presentation deck, complete with images, based on entered text.
Free, no-frills version of Stable Diffusion from its creator.
Official web app from the creator of Stable Diffusion. Users are given 25 free credits (~125 images), which do not renew, and then purchase additional credits as needed. DreamStudio prompt guide
AI tools for text to image, generative fill, text effects, generative recolor, 3D to image, and extend image (change the aspect ratio). Free plan provides 25 credits per month. Also included in Adobe Creative Cloud products including Express, Illustrator, Photoshop, and Stock.
Meta's image generation site that provides access to their Emu image-synthesis model, which was trained on 1.1 billion publicly visible Facebook and Instagram images Requires a Meta account, which can be connected to a Facebook or Instagram account. Also available via Messenger in messages by typing /imagine and then the text-to-image prompt.
Imagen 3 is Google’s latest text-to-image model, capable of generating photorealistic images with exceptional detail and fewer visual artifacts. It supports a wide range of artistic styles and formats. Currently available through ImageFX and Vertex AI.
Completely free text-to-image generator. Formerly called DALL·E mini but never associated with DALL·E or OpenAI. Designed by developer Boris Dayma.
AI image generator with its own models. Free users can amass 20 energy points, which regenerate 1-2 per hour. Standard images use 4 energy points. Free users are limited to 3 images generated with PRO models per day.
Text-to-image generator. Free version generates one image at a time; paid version generates four options. Images are editable with additional text prompts.
Ideogram is an AI image generator that claims to have solved a problem that plagues AI image generators -- the ability to generate coherent text within an image.
Modyfi is a collaborative, AI-native, web-based design and image creation platform that combines the design and image making tools with AI-powered creative technology
NeuralBlender is currently revamping with some unique AI features. During this transition period payment is disabled and NeuralBlender can be used for free.
Midjourney is a self-funded, independent research lab whose text-to-image generator creates the highest quality digital art. Currently considered one of the best, if not the best, image generator. There is currently no free tier for new users and prompts must be entered via Discord. 8 Tips For Writing Effective Midjourney Prompts.
Create Text to Speech, Speech to Speech, Dubbing, Text to SFX, or Voice Cloning
Microsoft Clipchamp: AI text to speech: all the features you should know about
AIVA (Artificial Intelligence Virtual Artist) is an AI-powered music generator that composes original and personalized soundtracks for various projects, such as videos, games, and movies. By leveraging advanced algorithms and deep learning, AIVA can create music in different styles and genres, offering users a range of presets and the ability to edit soundtracks.
This is the demo for MusicGen, Meta's music generating tool.
Soundful is an AI-powered music generator platform that enables creators to produce unique, royalty-free tracks with just a click of a button. The software uses complex algorithms to create customizable compositions across various genres and moods, catering to musicians, content creators, and casual listeners alike.
Stability AI's music creator
"Make a song about anything." Suno is an AI-powered music generator developed by Anthropic, allowing users to create new songs by simply describing the song they want to create.
"Imagine creating personalized music for your life: a ballad for a romantic date, a banger for a night out with friends, a lo-fi track for meditation, or an upbeat song for your child’s birthday. If you can describe it in text, you can now express it in music."
Hedra's platform allows users to generate videos with expressive and controllable human characters, enabling complete creative control over worlds, characters, and stories
Dream Machine is an AI model that makes high quality, realistic videos fast from text and images.
Pika leverages artificial intelligence to transform text-to-video, image-to-video, or video-to-video prompts into dynamic video content.
Text/image to video creator that generates 5-10 seconds of realistic video.
Upload a video to generate accompanying sound effects.
Tools > Voice typing
Includes automatic captions for uploaded videos
Click the "show captions" button during a Zoom session for live automatic captioning and transcript.
Upload an image to generate a description and alt-text.
A crowd-sourced list of AI-assisted coding tools.
GitHub Copilot is free to use for verified students, teachers, and maintainers of popular open source projects. If you are not a student, teacher, or maintainer of a popular open source project, you can try GitHub Copilot for free with a one-time 30-day trial.
The Generative AI Product Tracker lists generative AI products that are either marketed specifically towards postsecondary faculty or students or appear to be actively in use by postsecondary faculty or students for teaching, learning, or research activities. The Tracker is a living document, which we update regularly as new products enter the market or new information about existing products becomes available.
Our team developed a database of Artificial Intelligence (AI) applications useful for social science research. To be included in our database, the AI tool had to be useful for: 1) literature reviews, summaries, or writing, 2) data collection, analysis, or visualizations, or 3) research dissemination. In the database, we provide a name, description, and links to each of the AI tools that were current at the time of publication.
Includes AI Tools for Librarians tab. Complements Laura Abbene's AI Powered Tools & Resources document.
Poe by Quora is a unique platform that gives users access to multiple AI chatbots in one place. Includes its own GPT-3.5-turbo assistant, Claude, GPTs, LLaMa and Code LLaMa, and Gemini, Gemma, and PaLM, Mistral, Mixtral, and large collection of other models. Also includes a variety of specialized bots and image generators, including StableDiffusionXL and Playground.
Companion to The Rundown AI newsletter.
There's an AI for That (sponsored by the TeamSmart ChatGPT Chrome Extension)
"A curated directory of the latest AI tools & services"
"The Latest Source of AI Tools & Prompts"