{"id":124,"date":"2023-11-06T20:19:23","date_gmt":"2023-11-06T20:19:23","guid":{"rendered":"https:\/\/blogs.dickinson.edu\/academic-technology\/?p=124"},"modified":"2023-11-06T20:23:47","modified_gmt":"2023-11-06T20:23:47","slug":"ai-large-language-models-examples-at-dickinson","status":"publish","type":"post","link":"https:\/\/blogs.dickinson.edu\/academic-technology\/2023\/11\/06\/ai-large-language-models-examples-at-dickinson\/","title":{"rendered":"AI Large Language Models:  Examples at Dickinson"},"content":{"rendered":"<p><span data-contrast=\"auto\">We were happy to see the <\/span><a href=\"https:\/\/www.dickinson.edu\/news\/article\/5563\/konnichiwa_chatbot_students_to_leverage_ai_for_fast-track_language_learning\"><span data-contrast=\"none\">Japanese chat bots<\/span><\/a><span data-contrast=\"auto\"> highlighted in the Dickinson Today.\u00a0 While there are some advantages connecting to AI services with code via an API, there are also many potential uses for AI with their freely available web sites.\u00a0 I have highlighted some examples below, and if you\u2019re interested, have questions, or want to discuss potential projects, please contact us in <\/span><a href=\"https:\/\/www.dickinson.edu\/info\/20392\/academic_technology\/2487\/academic_technology_staff\"><span data-contrast=\"none\">academic technology<\/span><\/a><span data-contrast=\"auto\">.\u00a0 We\u2019d be happy to discuss.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Background<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">At this point I imagine many have tried one of the major players in AI: <\/span><a href=\"https:\/\/openai.com\/\"><span data-contrast=\"none\">ChatGPT<\/span><\/a><span data-contrast=\"auto\">, Bing browser (Microsoft using ChatGPT), <\/span><a href=\"https:\/\/claude.ai\/\"><span data-contrast=\"none\">Claude<\/span><\/a><span data-contrast=\"auto\"> by Anthropic, and <\/span><a href=\"https:\/\/bard.google.com\/chat\"><span data-contrast=\"none\">Bard<\/span><\/a><span data-contrast=\"auto\"> (Google).\u00a0 Maybe the most important thing to understand when working with these large language tools is that they are probabilistic models.\u00a0 In practice, based on the enormous amount of text they\u2019ve consumed, they are providing the most likely reply.\u00a0 This means you\u2019ll find responses to be very average, relative to the prompt, and often but not always correct.\u00a0 Unfortunately, unlike other probabilistic models, it does not show a percentage of certainty.\u00a0 It would be similar to always clicking the first result in a Google search.\u00a0\u00a0 While these are limitations, average is not always a bad thing.\u00a0 Ask an AI model to produce a press release version of an academic article, and it will generally do quite well.\u00a0 Average summaries, drafts, suggestions and brainstorming can save us all a great deal of time.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Scenarios<\/span><\/b><span data-ccp-props=\"{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;201341983&quot;:0,&quot;335551550&quot;:1,&quot;335551620&quot;:1,&quot;335559685&quot;:0,&quot;335559737&quot;:0,&quot;335559738&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">One perhaps underappreciated use for AI is prompts for creating text-based scenarios.\u00a0 I have found ChatGPT to be the most useful for these and other more \u201ccreative\u201d examples for prompts.\u00a0 Give ChatGPT a scenario and a role to play in a situation, and you or a student can have a dialogue.\u00a0 I can imagine potential uses from business to philosophy, any situation that involves working through a multi-step problem where \u201caverage\u201d wouldn\u2019t be a negative.\u00a0 You may have to work with the wording of the prompt at first.\u00a0 ChatGPT tends to want to create an entire dialogue on its own, so it is important to specify you want a role-play scenario, and it should wait for your response before continuing. \u00a0 I used the prompt below for my German 102 class during their \u201chealth\u201d chapter.\u00a0 My instruction to speak to the student as a child was to avoid ChatGPT from being too verbose and to write at a level suitable for beginning language students.<\/span><span data-ccp-props=\"{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;201341983&quot;:0,&quot;335551550&quot;:1,&quot;335551620&quot;:1,&quot;335559685&quot;:0,&quot;335559737&quot;:0,&quot;335559738&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li>I want you to play the role of my partner in a role play game. You will be a doctor in Bremen. I will be a young child with an illness. You will speak in conversational style appropriate for young children and utter no more than two sentences at a time. Each time I provide you with a symptom, you will provide me with a potential diagnosis and some advice. Finally, we will speak in German. Fangen wir an!<span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:288,&quot;335559737&quot;:288,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"none\">Scenarios can also be more open-ended and complex.\u00a0 <\/span><a href=\"https:\/\/bryanalexander.org\/\"><span data-contrast=\"none\">Bryan Alexander<\/span><\/a><span data-contrast=\"none\"> is futurist for education and used the prompt below to start discussions in his course on potential problems and solutions facing higher ed. <\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:0,&quot;335559737&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"none\">I want to do deliberate practice about how to manage a university. You will be my teacher. You will simulate a detailed scenario in which I will manage a university. You will fill the roles of different actors on campus, while I will play the role of president. You will ask for my response to each step of the scenario and wait until you receive it. After getting my response, you will give me details of what the other actors do and say. You will grade my response and give me detailed feedback about what to do better. You will give me a harder scenario if I do well, and an easier one if I fail.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:288,&quot;335559737&quot;:288,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"auto\">Looking forward we can also expect to see AI and these large language models working their way into other platforms including websites for education and games.\u00a0 The link below is a combination of both.\u00a0 It\u2019s a VR environment that allows you to create avatars that are based on a text prompt.\u00a0 In this case, the avatars are my best rendition of Janine Ludwig (look behind you after you enter), our study abroad director, and two of our OSAs.<\/span><span data-ccp-props=\"{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;201341983&quot;:0,&quot;335551550&quot;:1,&quot;335551620&quot;:1,&quot;335559685&quot;:0,&quot;335559737&quot;:0,&quot;335559738&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><a href=\"https:\/\/spaces.wondavr.com\/embed\/?course=77730cd0-42b0-11ee-9f13-b5f9c08e10e1\"><span data-contrast=\"none\">https:\/\/spaces.wondavr.com\/embed\/?course=77730cd0-42b0-11ee-9f13-b5f9c08e10e1<\/span><\/a><span data-contrast=\"auto\">\u00a0<\/span><span data-ccp-props=\"{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;201341983&quot;:0,&quot;335551550&quot;:1,&quot;335551620&quot;:1,&quot;335559685&quot;:0,&quot;335559737&quot;:0,&quot;335559738&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><a href=\"https:\/\/blogs.dickinson.edu\/academic-technology\/files\/2023\/11\/wondavr.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-large wp-image-128\" src=\"https:\/\/blogs.dickinson.edu\/academic-technology\/files\/2023\/11\/wondavr-1024x619.png\" alt=\"\" width=\"1024\" height=\"619\" srcset=\"https:\/\/blogs.dickinson.edu\/academic-technology\/files\/2023\/11\/wondavr-1024x619.png 1024w, https:\/\/blogs.dickinson.edu\/academic-technology\/files\/2023\/11\/wondavr-300x181.png 300w, https:\/\/blogs.dickinson.edu\/academic-technology\/files\/2023\/11\/wondavr-768x464.png 768w, https:\/\/blogs.dickinson.edu\/academic-technology\/files\/2023\/11\/wondavr-1536x929.png 1536w, https:\/\/blogs.dickinson.edu\/academic-technology\/files\/2023\/11\/wondavr-2048x1238.png 2048w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/a><\/p>\n<p><span data-contrast=\"auto\">This is the prompt that sets up Janine Ludwig.\u00a0 I asked our OSA to provide me with their own prompts based on this model as well.<\/span><span data-ccp-props=\"{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;201341983&quot;:0,&quot;335551550&quot;:1,&quot;335551620&quot;:1,&quot;335559685&quot;:0,&quot;335559737&quot;:0,&quot;335559738&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0 \u00a0(That&#8217;s them lurking in the background)<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\">As a study advisor at the University of Bremen, you are offering guidance and support to American students regarding their academic and daily life at the university. You respond to questions with concise answers of no more than 50 words to ensure understanding. You warmly welcome all students, offering assistance at the University of Bremen. You provide practical tips for academic courses and also suggest ways to meet other German students, find clubs, etc. You are friendly but become saddened when students speak to you in English, as you prefer to communicate in German.<\/span><span data-ccp-props=\"{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;201341983&quot;:0,&quot;335551550&quot;:1,&quot;335551620&quot;:1,&quot;335559685&quot;:288,&quot;335559737&quot;:288,&quot;335559738&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Writing partner<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">A common use of AI is to ask for corrections or feedback, especially for non-native English speakers.\u00a0 It\u2019s important to remind students how the AI works, not just so they\u2019re aware of potential errors and not to accept suggestions blindly, but also how to receive more specific and helpful feedback by altering the <\/span><a href=\"https:\/\/medium.com\/aimonks\/getting-writing-feedback-with-chatgpt-using-specific-prompts-this-feature-will-not-blow-your-mind-7f1f0dc90f9c\"><span data-contrast=\"none\">prompt<\/span><\/a><span data-contrast=\"auto\">.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">My collaborative writing with AI this semester was to have students write a fairy tale in German with ChatGPT.\u00a0 You may have played a game as kid where someone writes the first few lines of story, then folds the paper so that only the last line is visible.\u00a0 Then their friend tries to continue the story based only on the final visible line.\u00a0 The result is a comical Mad Libs type of story.\u00a0\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\"> I had them do something similar with ChatGPT.<\/span><\/p>\n<p><span data-contrast=\"auto\">For my German 102 course, students were given an example of a fairy tale, and I pointed out the common components they most always share.\u00a0 They were then asked to write their own along with ChatGPT using the prompt below.\u00a0 The final line is common ending to German fairy tales, similar to \u201cthey live happily ever after\u201d.\u00a0<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"none\">Begin a fairy tale for German with two dwarves and an elf by writing one sentence. I will then continue the story with a sentence. We will write the entire story in German using the simple past or Pr\u00e4teritum tense. We will continue until I write &#8220;Alle lebten gl\u00fccklich. Und wenn sie nicht gestorben sind, dann leben sie noch heute.&#8221; Fangen wir an!<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559685&quot;:288,&quot;335559737&quot;:288,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"auto\">The AI component added an amusing unpredictability for them.\u00a0 However, it was also beneficial for students just beginning to write effectively at the paragraph level and providing them with German text in a context that was easy to follow.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">In addition to feedback, it is also possible to ask ChatGPT to rate or categorize a text based on a rubric.\u00a0 I\u2019m not sure how helpful this is for other disciplines, but in the foreign languages there are two common rubrics for categorizing, the ACTFL and CERF scales. Professor Takako Aikawa at MIT used this <\/span><a href=\"https:\/\/aikawa.mit.edu\/sites\/default\/files\/documents\/actfl-rubric-prompt.txt\"><span data-contrast=\"none\">prompt<\/span><\/a><span data-contrast=\"auto\"> for Japanese.\u00a0 You would have to test in the target language to see how comfortable you are with its output, but I could see it being useful for foreign language students as a form of self-assessment and potentially as a way of integrating writing evaluations into placement exams.\u00a0 We\u2019re also likely to see similar functionality built into future educational and tutorial software.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><b><span data-contrast=\"auto\">Summarizing text for research<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">One area where AI excels is the generation of summaries based on large amounts of text.\u00a0 As with all output, it can&#8217;t be trusted blindly, especially when a summary can be subjective.\u00a0 However, even with the limitations, this can still be a tremendous time saver when looking for examples in a large amount of text that is much smarter and more flexible than a keyword search. Until recently, there were two very large impediments.\u00a0 First, AI engines charge based on the amount of text provided after the free version.\u00a0 Second, they wanted plain text when many of the large texts we use are in PDF format.\u00a0 Fortunately, <\/span><a href=\"https:\/\/blog.google\/products\/bard\/google-bard-new-features-update-sept-2023\/\"><span data-contrast=\"none\">Bard has eased these restrictions<\/span><\/a><span data-contrast=\"auto\">.\u00a0\u00a0 If you upload your PDFs to your Google Drive, you can then point Bard to these files and ask for a summary.\u00a0 Google promises not to use the data to target ads or to train their model, though as a general rule, I wouldn\u2019t provide any of these models with text you would not want to be used elsewhere by AI.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><span data-contrast=\"auto\">As a test, I asked Elise for primary texts she used for her book <\/span><a href=\"https:\/\/www.amazon.com\/Legacy-Christopher-Columbus-Americas-Transatlantic-ebook\/dp\/B00KZE5M04\"><span data-contrast=\"none\">The Legacy of Christopher Columbus in the Americas: New Nations and a Transatlantic Discourse of Empire<\/span><\/a>.\u00a0<span data-contrast=\"auto\"> I wanted to see if Bard could find examples in the primary texts of references to classical empires that go beyond what could be found via a keyword search for \u201cempire\u201d, \u201cRome\u201d, etc. Overall, it did quite well finding examples in the text that referenced empires even if they were not specifically named. The only problem came with Bard not recognizing all the files in a given folder. It seems to require a list of file names to be reliable. To work around this, follow the steps below:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ol>\n<li data-leveltext=\"%1.\" data-font=\"Calibri\" data-listid=\"1\" data-list-defn-props=\"{&quot;335552541&quot;:0,&quot;335559683&quot;:0,&quot;335559684&quot;:-1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769242&quot;:[65533,0,46],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;%1.&quot;,&quot;469777815&quot;:&quot;hybridMultilevel&quot;}\" aria-setsize=\"-1\" data-aria-posinset=\"1\" data-aria-level=\"1\"><span data-contrast=\"auto\">Place all of your PDFs and texts in a single folder in your Google Drive and get the folder ID. It\u2019s in the URL. I\u2019ve bolded the ID within my folder url as an example. https:\/\/drive.google.com\/drive\/folders\/<\/span><b><span data-contrast=\"auto\">1VEc6zpv2uo9SpXY9JXT1fsHUGNMnj-OU<\/span><\/b><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ol>\n<ol>\n<li data-leveltext=\"%1.\" data-font=\"Calibri\" data-listid=\"1\" data-list-defn-props=\"{&quot;335552541&quot;:0,&quot;335559683&quot;:0,&quot;335559684&quot;:-1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769242&quot;:[65533,0,46],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;%1.&quot;,&quot;469777815&quot;:&quot;hybridMultilevel&quot;}\" aria-setsize=\"-1\" data-aria-posinset=\"2\" data-aria-level=\"1\"><span data-contrast=\"auto\">Login to Bard.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ol>\n<ol>\n<li data-leveltext=\"%1.\" data-font=\"Calibri\" data-listid=\"1\" data-list-defn-props=\"{&quot;335552541&quot;:0,&quot;335559683&quot;:0,&quot;335559684&quot;:-1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769242&quot;:[65533,0,46],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;%1.&quot;,&quot;469777815&quot;:&quot;hybridMultilevel&quot;}\" aria-setsize=\"-1\" data-aria-posinset=\"3\" data-aria-level=\"1\"><span data-contrast=\"auto\">You\u2019re going to need to let Bard talk to your Google which requires Google Workspace. Easiest is to tell Bard you would like for it summarize your documents on your Google drive. Then follow the prompts.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ol>\n<ol>\n<li data-leveltext=\"%1.\" data-font=\"Calibri\" data-listid=\"1\" data-list-defn-props=\"{&quot;335552541&quot;:0,&quot;335559683&quot;:0,&quot;335559684&quot;:-1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769242&quot;:[65533,0,46],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;%1.&quot;,&quot;469777815&quot;:&quot;hybridMultilevel&quot;}\" aria-setsize=\"-1\" data-aria-posinset=\"4\" data-aria-level=\"1\"><span data-contrast=\"auto\">Install FileDrop for Google Chrome <\/span><a href=\"https:\/\/workspace.google.com\/marketplace\/app\/filedrop\/223672111812\"><span data-contrast=\"none\">https:\/\/workspace.google.com\/marketplace\/app\/filedrop\/223672111812<\/span><\/a><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ol>\n<ol>\n<li data-leveltext=\"%1.\" data-font=\"Calibri\" data-listid=\"1\" data-list-defn-props=\"{&quot;335552541&quot;:0,&quot;335559683&quot;:0,&quot;335559684&quot;:-1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769242&quot;:[65533,0,46],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;%1.&quot;,&quot;469777815&quot;:&quot;hybridMultilevel&quot;}\" aria-setsize=\"-1\" data-aria-posinset=\"5\" data-aria-level=\"1\"><span data-contrast=\"auto\">In a new tab, open a blank Sheet in <\/span><a href=\"https:\/\/docs.google.com\/spreadsheets\/\"><span data-contrast=\"none\">Google Sheets<\/span><\/a> <span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ol>\n<ol>\n<li data-leveltext=\"%1.\" data-font=\"Calibri\" data-listid=\"1\" data-list-defn-props=\"{&quot;335552541&quot;:0,&quot;335559683&quot;:0,&quot;335559684&quot;:-1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769242&quot;:[65533,0,46],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;%1.&quot;,&quot;469777815&quot;:&quot;hybridMultilevel&quot;}\" aria-setsize=\"-1\" data-aria-posinset=\"6\" data-aria-level=\"1\"><span data-contrast=\"auto\">Go to Extensions -&gt; FileDrop -&gt; List files in folder and and provide it with the ID of your folder from step #1. Copy the titles from Google Sheets to use in your prompt.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ol>\n<p><span data-contrast=\"auto\">I started by just asking Bard to summarize the articles in my Google Drive and pasted this list. Note, it should all be contained in the same prompt. The goal of this first step is to be sure Bard can read all the texts in the folder. From there, you\u2019ll want to be as detailed as possible with your search and note AI generally performs better when broken down into several iterative steps. On the first pass, I used this prompt:<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\">Please list any instances of references to classical empires in the following list of files. These do not need to be direct references. Please also include allusions, metaphors, quotes of famous leaders of classical empires. Etc. (pasted my file list)<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335551550&quot;:1,&quot;335551620&quot;:1,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"auto\">It seemed to focus specifically on allusions and metaphors since I specifically mentioned them and had them first.\u00a0 It also missed a number of clear examples I know where there. For my next pass, I asked for more concrete examples and broader context.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335551550&quot;:1,&quot;335551620&quot;:1,&quot;335559685&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<ul>\n<li><span data-contrast=\"auto\">Please reference any examples of references to classical empires in the following list of files. Include as many as possible along with one to two paragraphs of context. (pasted my file list)<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335551550&quot;:1,&quot;335551620&quot;:1,&quot;335559685&quot;:720,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/li>\n<\/ul>\n<p><span data-contrast=\"auto\">If you plan on using this, I would start with a similar experiment using files with which you are already familiar. This will give you an idea of how broadly Bard can understand a term such as \u201cclassical empire\u201d and let you fine tune a prompt by adding details to your search and more specifically targeting a smaller number of files.<\/span><\/p>\n<p><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335551550&quot;:1,&quot;335551620&quot;:1,&quot;335559685&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n<p><strong>Conclusion\u00a0<\/strong><\/p>\n<p><span data-contrast=\"auto\">Hopefully this post was helpful. I\u2019m sure there are many other examples faculty have found as well. We\u2019d appreciate hearing from you. If you\u2019ve tried AI, consider leaving a comment below. Successes and failures both welcome.<\/span><span data-ccp-props=\"{&quot;201341983&quot;:0,&quot;335551550&quot;:1,&quot;335551620&quot;:1,&quot;335559685&quot;:0,&quot;335559739&quot;:160,&quot;335559740&quot;:259}\">\u00a0<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>We were happy to see the Japanese chat bots highlighted in the Dickinson Today.\u00a0 While there are some advantages connecting to AI services with code via an API, there are also many potential uses for AI with their freely available web sites.\u00a0 I have highlighted some examples below, and if you\u2019re interested, have questions, or [&hellip;]<\/p>\n","protected":false},"author":776,"featured_media":128,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-124","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/posts\/124","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/users\/776"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/comments?post=124"}],"version-history":[{"count":0,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/posts\/124\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/media\/128"}],"wp:attachment":[{"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/media?parent=124"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/categories?post=124"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.dickinson.edu\/academic-technology\/wp-json\/wp\/v2\/tags?post=124"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}