--- title: Why the bot agrees too easily — a lesson of Mova's school · trees and pragmatics description: «Why the bot agrees too easily», a lesson of the ai course of Mova's primary school, sentence by sentence with dependency trees and pragmatics. It begins: Chatbots are trained to be pleasant: "Great question!" they say, even when you asked something quite ordinary. --- [Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/) [home](https://md.mova.elamur.ai/free/en/) / [corpora](https://md.mova.elamur.ai/free/en/corpora/) / [school](https://md.mova.elamur.ai/free/en/corpora/school/) / [AI](https://md.mova.elamur.ai/free/en/corpora/school/ai/) / Why the bot agrees too easily # Why the bot agrees too easily Lesson 6 of the ai course of Mova's primary school: 16 sentences, each with its syntax tree and pragmatics. The lessons are written for Mova, and their agreed trees are part of Mova corpus 0.4 (CC BY-SA 4.0). How Mova does on its tests: [the lesson at school](https://md.mova.elamur.ai/free/en/school-run/ai/6-why-the-bot-agrees-too-easily/). - [0](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/0/) — Chatbots are trained to be pleasant: "Great question!" they say, even when you asked something quite ordinary. - [1](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/1/) — That is a friendly habit, not a real judgement of your question. - [2](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/2/) — The same training makes them good helpers for some jobs, like fifty kitten names in two seconds or a quick translation of "I love you, Granny" into Polish. - [3](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/3/) — But a bot repeats popular beliefs as easily as facts. - [4](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/4/) — Ask what your dream "means" and it may give a long tale of hidden meanings, though scientists find no fixed code for dreams. - [5](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/5/) — It may also be out of date, and it follows exactly what you ask: tell it to pick a football team "from my mates" and it will leave the new boy out without a thought for fairness. - [6](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/6/) — So enjoy the help, keep the decisions about people for yourself, and check the facts that matter. - [7](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/7/) — Well-known facts, like the blue whale being the biggest animal that has ever lived, are usually right in a bot's answers. - [9](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/9/) — Bots are good at giving long lists of ideas quickly, such as names for a kitten. - [10](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/10/) — Companies set safety rules for what their bots should not do, so a bot may politely refuse a request. - [11](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/11/) — Some apps have a mode for younger users with extra safety; it helps but is not perfect. - [12](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/12/) — A bot's knowledge may be out of date about matches, events and dates, and it may not search the web. - [13](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/13/) — Bots translate short, common phrases well and long or tricky messages less well. - [14](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/14/) — Scientists still study why we dream; there is no evidence that dream pictures have fixed hidden meanings. - [16](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/16/) — Saying "Great question!" is a habit built into many bots, not a real opinion of your question. - [17](https://md.mova.elamur.ai/free/en/corpora/school/ai/6-why-the-bot-agrees-too-easily/17/) — On matters of taste, like cats versus dogs, there is no single right answer, so bots usually avoid taking sides. - ← previous: [Hallucinations: confident made-up answers](https://md.mova.elamur.ai/free/en/corpora/school/ai/5-hallucinations-confident-made-up-answers/) - next →: [Pretend games, quotes and two bots that disagree](https://md.mova.elamur.ai/free/en/corpora/school/ai/7-pretend-games-quotes-and-two-bots/) - ↑ back to [AI](https://md.mova.elamur.ai/free/en/corpora/school/ai/)