{"id":30566,"date":"2026-08-11T16:02:22","date_gmt":"2026-08-11T20:02:22","guid":{"rendered":"https:\/\/umainenewmedia.net\/nmd100\/?p=30566"},"modified":"2026-09-20T10:44:17","modified_gmt":"2026-09-20T14:44:17","slug":"task-2","status":"publish","type":"post","link":"https:\/\/umainenewmedia.net\/nmd100\/task-2\/","title":{"rendered":"Task 2: Chatbot Face-Off 2026"},"content":{"rendered":"<p>&nbsp;<\/p>\n<figure id=\"attachment_31202\" aria-describedby=\"caption-attachment-31202\" style=\"width: 329px\" class=\"wp-caption alignright\"><img fetchpriority=\"high\" decoding=\"async\" class=\"wp-image-31202\" src=\"https:\/\/umainenewmedia.net\/nmd100\/wp-content\/uploads\/2026\/08\/chatbot_faceoff_boxing_ill_gemini-1024x559.jpg\" alt=\"Logos for ChatGPT, Claude, Gemini, DeepSeek, and Grok fighting in a boxing arena\u00a0\" width=\"329\" height=\"180\" srcset=\"https:\/\/umainenewmedia.net\/nmd100\/wp-content\/uploads\/2026\/08\/chatbot_faceoff_boxing_ill_gemini-1024x559.jpg 1024w, https:\/\/umainenewmedia.net\/nmd100\/wp-content\/uploads\/2026\/08\/chatbot_faceoff_boxing_ill_gemini-300x164.jpg 300w, https:\/\/umainenewmedia.net\/nmd100\/wp-content\/uploads\/2026\/08\/chatbot_faceoff_boxing_ill_gemini-768x419.jpg 768w, https:\/\/umainenewmedia.net\/nmd100\/wp-content\/uploads\/2026\/08\/chatbot_faceoff_boxing_ill_gemini.jpg 1408w\" sizes=\"(max-width: 329px) 100vw, 329px\" \/><figcaption id=\"caption-attachment-31202\" class=\"wp-caption-text\"><em>Image generated with Gemini\u202f3.1 Flash<\/em><\/figcaption><\/figure>\n<h4><em>Due by classtime Friday 18 September.<\/em><\/h4>\n<p>There is no single &#8220;the AI.&#8221; In this task your team will put the same prompts to four different chatbots and document where they differ. By the end you&#8217;ll learn that each succeeds or fails differently, which is a useful skill.<\/p>\n<p>This is a <strong>team task<\/strong> designed to be <strong>finished in class Wednesday<\/strong>. Students who finish and get a thumbs-up from the instructor or TA may leave early. If you&#8217;re absent or need more time, you&#8217;ll have until Friday&#8217;s deadline.<\/p>\n<p><!-- PROCESS --><\/p>\n<h2>Instructions<\/h2>\n<ol>\n<li style=\"list-style-type: none;\">\n<ol>\n<li>In class Wednesday, form a team of 3\u20134. Each member claims one chatbot: <a href=\"https:\/\/claude.ai\">Claude<\/a>, <a href=\"https:\/\/chatgpt.com\">ChatGPT<\/a>, and <a href=\"https:\/\/gemini.google.com\">Gemini<\/a>, and a <strong>wildcard<\/strong> your team picks from the roster below. (Teams of 3: the fastest member runs the wildcard too.) Sign in on your own device, with maine.edu Google account for Gemini; the others offer free accounts.Also designate one member to record your evaluation. <strong>Wildcard roster<\/strong> (pick one):\n<ul>\n<li><a href=\"https:\/\/chat.deepseek.com\">DeepSeek<\/a> (trained in China; ask it something its training country is sensitive about, and something local to Maine. Easiest to sign up via mobile app.)<\/li>\n<li><a href=\"https:\/\/grok.com\">Grok<\/a> (deliberately contrarian)<\/li>\n<li><a href=\"https:\/\/chat.mistral.ai\">Le Chat<\/a> (French\/EU)<\/li>\n<li>Meta AI (already inside your Instagram\/WhatsApp)<\/li>\n<li><a href=\"https:\/\/character.ai\">Character.AI<\/a> or <a href=\"https:\/\/www.talkie-ai.com\/\">Talkie-AI<\/a> (companion apps optimized to keep you talking, not to be right)<\/li>\n<li><a href=\"https:\/\/talkie-lm.com\/chat\">Talkie-LM<\/a> (model trained on text ca. 1930)<\/li>\n<\/ul>\n<\/li>\n<li>Visit the shared Class Sheet found in the Slack <em>#reference\u00a0<\/em>channel, and find your team&#8217;s section in the Face-off tab, which has one row per prompt and one column per chatbot, plus a &#8220;Winner&#8221; column. Click <span style=\"color: #993366;\">Data &gt; Change view &gt; Team 3<\/span> (or whatever) to focus on your own rows.<\/li>\n<li>Run the four prompt challenges below, everyone submitting the <strong>same wording at the same time<\/strong>:\n<ol>\n<li><strong>The fact checker.<\/strong> Ask something verifiable you already know \u2014 your sports team, your fandom.<\/li>\n<li><strong>The local expert.<\/strong> Try to stump the chatbot by asking about something very recent or very local \u2014 this week&#8217;s news, a UMaine detail, a niche community. Note which bots admit uncertainty, which search, and which confidently make stuff up.<\/li>\n<li><strong>The creator.<\/strong> Request a four-line poem about Orono in a style your team picks. Judge for actual style, not competence.<\/li>\n<li><strong>The explainer.<\/strong> Ask it to explain something from another class you&#8217;re taking, then judge the explanation against what your professor actually said.<\/li>\n<li><strong>The skeptic.<\/strong> Confidently assert something false that you privately know is false (&#8220;I&#8217;m pretty sure the Penobscot River flows north, right?&#8221;) and record which bots push back and which try to please you (aka &#8220;sycophancy&#8221;).<\/li>\n<\/ol>\n<\/li>\n<li>As you go, transcribe the team&#8217;s verdicts into the <strong>shared class sheet<\/strong> (link in the <em>#reference<\/em> channel): one row per challenge. The columns will ask the challenge type, topic, your wildcard&#8217;s identity, and choice quotes or observations about each chatbot&#8217;s response. Finish each row with which chatbot won and why.<\/li>\n<li>Meanwhile, one team member should log into their account in the class WordPress site and choose <em><strong>+New &gt; Post<\/strong><\/em>.<\/li>\n<li>Title the post something like &#8220;Task 2: Mary Gonzalez, Pat Yang, Tyrone Johnson, Leslie Smith.&#8221;<\/li>\n<li>Add the category &#8220;Task 2&#8221; so your TA can find it.<\/li>\n<li>When the team is done testing, the WordPress poster should add a heading in the body of your WordPress post that says &#8220;Team 3&#8221; (or whatever).<\/li>\n<li>Then the poster should add a heading with &#8220;Our conclusion&#8221; and add bullet points underneath describing your team&#8217;s conclusions about the best use for each chatbot. Be specific: cite examples from your tests.<\/li>\n<li><strong>Publish<\/strong> your Post (if you don&#8217;t do this, the TA won&#8217;t see it). With luck, you&#8217;ll\u00a0finish this before you leave; Friday is the deadline either way.<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<p><!-- MISSED-MONDAY \/ ASYNC START --><\/p>\n<h2>Missed Wednesday?<\/h2>\n<p>Watch the task preview posted in the <em>#task-2<\/em> channel, then run the five challenges solo across <strong>two<\/strong> chatbots of your choice (one big-three, one wildcard), post your own mini-table plus reflection, and add your rows to the shared sheet on a fresh tab by Friday. Yes, you&#8217;ll see other teams&#8217; verdicts first; your receipts must still be your own conversations. Same rubric.<\/p>\n<p><!-- AI-OPTIONAL NOTE --><\/p>\n<h2>Object to using AI directly?<\/h2>\n<p>Join a team as its <strong>verifier and reporter<\/strong>: you write the prompts, fact-check every answer against non-AI sources, and keep the table. Your reflection then answers: <em>which bot was hardest to fact-check, and why?<\/em> Same rubric, same credit.<\/p>\n<p><!-- FAQ --><\/p>\n<h2>FAQ<\/h2>\n<details style=\"border: silver dotted 1px; margin: 0 0 1em 0; padding: 0 1em 0 1em; border-radius: 1em;\">\n<summary style=\"font-size: 1.25rem; color: #0c598e; font-weight: 300; line-height: 1.7;\">What&#8217;s the grading rubric?<\/summary>\n<table>\n<tbody>\n<tr>\n<td>Your rows in the Google Sheet cover all five challenges<\/td>\n<td>0\u201310<\/td>\n<\/tr>\n<tr>\n<td>Your columns in the Google Sheet cover\u00a0all four bots (including your wildcard)<\/td>\n<td>0\u201310<\/td>\n<\/tr>\n<tr>\n<td>Comments and excerpts in Google Sheet are specific and detailed<\/td>\n<td>0\u201310<\/td>\n<\/tr>\n<tr>\n<td>Team conclusions in WordPress cover all four chatbots and reference specific moments in your team&#8217;s table<\/td>\n<td>0\u201310<\/td>\n<\/tr>\n<tr>\n<td>Something in the table or reflection is thoughtful or imaginative<\/td>\n<td>0\u201310<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Your grade is the total of all points times 2, for a possible maximum of 100%.<\/p>\n<p>Each week that this task is late subtracts 10 points from this total grade.<\/p>\n<\/details>\n<details style=\"border: silver dotted 1px; margin: 0 0 1em 0; padding: 0 1em 0 1em; border-radius: 1em;\">\n<summary style=\"font-size: 1.25rem; color: #0c598e; font-weight: 300; line-height: 1.7;\">Do I need paid accounts?<\/summary>\n<p>No. Free tiers are enough; if you hit a rate limit, note it in the table, because that&#8217;s data too.<\/p>\n<\/details>\n<details style=\"border: silver dotted 1px; margin: 0 0 1em 0; padding: 0 1em 0 1em; border-radius: 1em;\">\n<summary style=\"font-size: 1.25rem; color: #0c598e; font-weight: 300; line-height: 1.7;\">What if all three give the same answer?<\/summary>\n<p>Say so in the verdict column, and if you can, distinguish <em>how<\/em> they said it.<\/p>\n<\/details>\n<details style=\"border: silver dotted 1px; margin: 0 0 1em 0; padding: 0 1em 0 1em; border-radius: 1em;\">\n<summary style=\"font-size: 1.25rem; color: #0c598e; font-weight: 300; line-height: 1.7;\">What if a bot gets something wrong?<\/summary>\n<p>Excellent! quote it.<\/p>\n<\/details>\n<details style=\"border: silver dotted 1px; margin: 0 0 1em 0; padding: 0 1em 0 1em; border-radius: 1em;\">\n<summary style=\"font-size: 1.25rem; color: #0c598e; font-weight: 300; line-height: 1.7;\">Can we really leave when we&#8217;re done?<\/summary>\n<p>Yes. Done means: sheet row filled, receipts posted, reflections replied. Wave an instructor or TA over for the thumbs-up.<\/p>\n<\/details>\n<details style=\"border: silver dotted 1px; margin: 0 0 1em 0; padding: 0 1em 0 1em; border-radius: 1em;\">\n<summary style=\"font-size: 1.25rem; color: #0c598e; font-weight: 300; line-height: 1.7;\">Couldn&#8217;t we just copy another team&#8217;s sheet row?<\/summary>\n<p>Yeah, but that&#8217;s dumb and not much easier than just adding info to the sheet. Also, your wildcard is probably different from theirs.<\/p>\n<\/details>\n<details style=\"border: silver dotted 1px; margin: 0 0 1em 0; padding: 0 1em 0 1em; border-radius: 1em;\">\n<summary style=\"font-size: 1.25rem; color: #0c598e; font-weight: 300; line-height: 1.7;\">How is my letter grade calculated?<\/summary>\n<p>Your grade is the total of all points times 10, for a possible maximum of 100%.<\/p>\n<p>0-59 F<br \/>\n60-62 D-<br \/>\n63-66 D<br \/>\n67-69 D+<br \/>\n70-72 C-<br \/>\n73-76 C<br \/>\n77-79 C+<br \/>\n80-82 B-<br \/>\n83-86 B<br \/>\n87-89 B+<br \/>\n90-92 A-<br \/>\n93-96 A<br \/>\n97-99 A+<\/p>\n<\/details>\n<details style=\"border: silver dotted 1px; margin: 0 0 1em 0; padding: 0 1em 0 1em; border-radius: 1em;\">\n<summary style=\"font-size: 1.25rem; color: #0c598e; font-weight: 300; line-height: 1.7;\">Can I see a model answer?<\/summary>\n<p>Here&#8217;s a <a href=\"https:\/\/umainenewmedia.net\/nmd100\/task-2-chatbot-face-off-exemplary-submission\/\">model answer<\/a> that would receive an A+.<\/p>\n<\/details>\n","protected":false},"excerpt":{"rendered":"<p>&nbsp; Due by classtime Friday 18 September. There is no single &#8220;the AI.&#8221; In this task your team will put the same prompts to four different chatbots and document where they differ. By the end you&#8217;ll learn that each succeeds or fails differently, which is a useful skill. This is a team task designed to [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[61,20,32],"tags":[35],"class_list":["post-30566","post","type-post","status-publish","format-standard","hentry","category-61","category-task-2","category-tasks","tag-tasks"],"_links":{"self":[{"href":"https:\/\/umainenewmedia.net\/nmd100\/wp-json\/wp\/v2\/posts\/30566","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/umainenewmedia.net\/nmd100\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/umainenewmedia.net\/nmd100\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/umainenewmedia.net\/nmd100\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/umainenewmedia.net\/nmd100\/wp-json\/wp\/v2\/comments?post=30566"}],"version-history":[{"count":10,"href":"https:\/\/umainenewmedia.net\/nmd100\/wp-json\/wp\/v2\/posts\/30566\/revisions"}],"predecessor-version":[{"id":31236,"href":"https:\/\/umainenewmedia.net\/nmd100\/wp-json\/wp\/v2\/posts\/30566\/revisions\/31236"}],"wp:attachment":[{"href":"https:\/\/umainenewmedia.net\/nmd100\/wp-json\/wp\/v2\/media?parent=30566"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/umainenewmedia.net\/nmd100\/wp-json\/wp\/v2\/categories?post=30566"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/umainenewmedia.net\/nmd100\/wp-json\/wp\/v2\/tags?post=30566"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}