{"id":9703,"date":"2023-10-07T11:09:16","date_gmt":"2023-10-07T09:09:16","guid":{"rendered":"https:\/\/www.lesestunden.de\/?p=9703"},"modified":"2025-08-26T22:59:01","modified_gmt":"2025-08-26T20:59:01","slug":"ulysses-gemeinsam-mit-einer-ki-buecher-lesen","status":"publish","type":"post","link":"https:\/\/www.lesestunden.de\/en\/2023\/10\/ulysses-reading-books-together-with-an-ai\/","title":{"rendered":"Ulysses: Reading books together with an AI"},"content":{"rendered":"\r\n

Ulysses<\/em> by James Joyce is considered one of the most difficult works in world literature. It is packed with countless, often subtle and hard-to-grasp allusions and references to mythology, politics, religion, current events, and other literary works. Between the chapters, a wide variety of stylistic devices are used, including the stream-of-consciousness technique, which makes reading even more confusing. I wondered whether ChatGPT might be a good tool to better understand this book\u2014whether a joint reading experience supported by ChatGPT could be a wonderful complement that turns reading this work into a light and relaxing journey into Joyce\u2019s world. I tried it out, and here\u2019s what I found: is ChatGPT a good reading companion?<\/p>\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n

High-quality new editions of classics often offer not only a modern translation but also an extensive appendix with numerous annotations. These serve to provide readers with additional information and make the text and its background more accessible. There are books where this is a pleasant addition, but not strictly necessary. And then there are books like Ulysses<\/em> by James Joyce. The text is so inaccessible and dense that the usual annotations completely fail, leaving the reader in the dark\u2014with just a few marginal notes, there\u2019s little help to be found.<\/p>\r\n\r\n\r\n\r\n

There is a commented edition of Ulysses<\/em>\u2014a massive tome that provides explanations and notes on every page surrounding the original text. However, this makes reading even more exhausting. Wouldn\u2019t it be much better to ask ChatGPT instead? After all, you can explicitly ask questions, request explanations for individual passages, or have entire chapters summarized. And ChatGPT should be quite familiar with Ulysses<\/em>, since scholars have been analyzing and dissecting the work for over a hundred years. It\u2019s safe to assume that several essays\u2014and perhaps even the entire text\u2014are part of ChatGPT\u2019s training data. That might not be the case with lesser-known books, but Ulysses<\/em> seems like the perfect candidate for such an experiment.<\/p>\r\n\r\n\r\n\r\n

So, I read the first chapter, which I found quite understandable. The second chapter was already tougher, but still somewhat manageable. The third chapter, however, is completely confusing. In it, Stephen takes a walk by the sea, and the reader experiences his erratic thoughts, memories, and the walk itself\u2014fully immersed in Joyce\u2019s stream of consciousness. It\u2019s utterly bewildering, and this jumble is almost impossible to untangle in a single reading. Chapter seven is also extreme, where Bloom moves among journalists and newspapermen, with numerous characters engaging in conversation without introduction. The tone of the journalists\u2014casual, disrespectful, often cynical\u2014is captured very well, similar to other novels that critically depict the profession. But the content itself is difficult to grasp. Some chapters, such as the sixth, \u201cHades,\u201d are easier to follow when Bloom is actually out and about, but even then, one gets the feeling that much slips by unnoticed. There are simply many sections that are completely incomprehensible and utterly confusing.<\/p>\r\n\r\n\r\n\r\n

When you start asking ChatGPT about the content of individual chapters, you do get usable answers. However, these are extremely condensed. Looking at the Wikipedia<\/a> article for the book, you\u2019ll find a detailed list of each chapter\u2019s main themes and ideas. ChatGPT\u2019s answers are roughly on this level when you simply ask about a chapter. You can easily ask, \u201cWhat happens in the first chapter of Ulysses<\/em>?\u201d and get a short summary. That\u2019s fine for the very difficult third chapter too\u2014but it doesn\u2019t really get you much further.<\/p>\r\n\r\n\r\n\r\n

So I asked further: \u201cWhich foreign-language passages appear in the third chapter? Translate them for me.\u201d<\/em> ChatGPT listed three sample quotes that I couldn\u2019t find in the text. When I asked for all French quotations, it gave me two (which I also couldn\u2019t find) and claimed there were no others. Here, ChatGPT seems to fail\u2014and when I compared it with a list<\/a> I found online, the human research was clearly more reliable and complete.<\/p>\r\n\r\n\r\n\r\n

Next, I wanted to know what the characters in the seventh chapter (the one with the journalists and their confusing dialogue) are actually talking about. Once again, the answer was very superficial and abstract, appearing incomplete and not particularly illuminating. When I asked for examples, ChatGPT referred to a few individual words, but overall remained at a high level of abstraction. For someone who understands almost nothing of that chapter, this offers no help or orientation.<\/p>\r\n\r\n\r\n\r\n

In this way, I tried to extract more information from ChatGPT\u2014and it turned out to be surprisingly tedious. You have to pull everything out of the AI bit by bit, and it becomes clear that it is optimized for providing summarized answers. Even though ChatGPT may seem too verbose in other contexts, when dealing with a text like Ulysses<\/em>, its answers are far too brief. Detailed questions are often met with general, abstract statements such as: \u201cIt is important to note that \u2018Ulysses\u2019 is a very complex work with many layers and levels of meaning, which is why it is considered one of the most significant works of modern literature by many readers and critics.\u201d<\/em> Attempting to group chapters thematically and have ChatGPT explain sections only worked moderately well. For instance, the supposed visit to the aunt in the third chapter wasn\u2019t mentioned at all, and later sections were explained so abstractly that it was difficult to see how they related to the actual text (the dog and other key elements were not mentioned at all).<\/p>\r\n\r\n\r\n\r\n

I admit that Ulysses<\/em> is a tough nut to crack\u2014for human readers and therefore for AI as well. But ChatGPT\u2019s explanations did not help me understand the chapters better or grasp their details. I also tried asking about individual passages\u2014for example, \u201cWhat is the fourth paragraph in the third chapter, and what is it about?\u201d<\/em> But soon, incorrect answers appeared, with wrong text excerpts that couldn\u2019t be found in the book (not even when considering translation differences). I was never sure whether ChatGPT\u2019s statements were actually correct. Since it never quoted directly from the text, it was impossible to tell where the information came from, whether it was complete, or even accurate. This, of course, is a fundamental issue with ChatGPT\u2014one that becomes particularly obvious when reading a work full of dense, ambiguous passages like this one.<\/p>\r\n\r\n\r\n\r\n

Reading Ulysses<\/em> is hard work, and anyone who wants to truly understand the book rather than just skim through it must study it thoroughly. You need to go through it section by section, sentence by sentence, let it sink in, and bring along the necessary background knowledge to grasp the subtle allusions and humor. As a source or aid, ChatGPT seemed of little help here. If you want to go deep, you must ask very precise questions, continuously refine the answers, and still can\u2019t be sure whether what you get is accurate. For a superficial overview, ChatGPT seemed fine\u2014but even here, I found the Wikipedia article or a quick Google search much clearer and more helpful.<\/p>\r\n\r\n\r\n\r\n

I should add that I find the current hype around artificial intelligence very exciting\u2014and ChatGPT is a brilliant tool. Many things can be done wonderfully with it, and I\u2019ve already connected the OpenAI API to a private project with excellent results. As with anything, there are use cases where ChatGPT works great, and others where it\u2019s currently less suitable. You can also see how ChatGPT keeps improving and its knowledge base expanding. Just a few days ago, it was reported that ChatGPT now has access to the internet<\/a> and is no longer limited to information up to September 2021. And these improvements are noticeable. Shortly after ChatGPT\u2019s public release, I asked, \u201cWhat races exist in Tad Williams\u2019s Osten Ard?\u201d\u2014and the answer was complete nonsense<\/a>. Now the question is answered correctly. It\u2019s only a matter of time before ChatGPT is trained on more recent books as well. For example, I copied one of Selma Lagerl\u00f6f\u2019s love stories<\/a> into ChatGPT (in several chunks, since the input field is limited) and then asked questions about the story\u2014and that worked wonderfully.<\/p>\r\n\r\n\r\n\r\n

Conclusion:<\/strong> Of course, I made it too easy for myself and my expectations were too high. My hope was that ChatGPT would take a chapter and explain it in detail\u2014what it\u2019s about, clarify difficult passages on its own, translate foreign-language quotes, group and explain related passages. You can perhaps get this kind of information out of ChatGPT somehow, but it\u2019s tedious and comes with the uncertainty of possible inaccuracies. Reading Ulysses<\/em> therefore remains a challenging endeavor, and anyone seeking a deep understanding of the text will not get it handed to them\u2014they\u2019ll have to engage deeply with each chapter, research, consult additional sources, and bring a great deal of patience.<\/p>\r\n\r\n","protected":false},"excerpt":{"rendered":"

Ulysses by James Joyce is considered one of the most difficult works in world literature. It is packed with countless, often subtle and hard-to-grasp allusions and references to mythology, politics, religion, current events, and other literary works. Between the chapters, a wide variety of stylistic devices are used, including the stream-of-consciousness technique, which makes reading … <\/p>\n

Continue reading “Ulysses: Reading books together with an AI”<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":9705,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"slim_seo":{"title":"Ulysses: Gemeinsam mit einer KI B\u00fccher lesen - lesestunden","description":"Ulysses von James Joyce gilt als eines der am schwersten zug\u00e4nglichen Werke der Weltliteratur. Es ist vollgepackt mit zahlreichen oft subtilen und schwer verst\u00e4"},"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_feature_clip_id":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_post_was_ever_published":false},"categories":[308],"tags":[],"class_list":["post-9703","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence"],"jetpack_featured_media_url":"https:\/\/www.lesestunden.de\/wp-content\/uploads\/2023\/10\/ulysses_ki.jpg","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/www.lesestunden.de\/en\/wp-json\/wp\/v2\/posts\/9703","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.lesestunden.de\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.lesestunden.de\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.lesestunden.de\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.lesestunden.de\/en\/wp-json\/wp\/v2\/comments?post=9703"}],"version-history":[{"count":0,"href":"https:\/\/www.lesestunden.de\/en\/wp-json\/wp\/v2\/posts\/9703\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.lesestunden.de\/en\/wp-json\/wp\/v2\/media\/9705"}],"wp:attachment":[{"href":"https:\/\/www.lesestunden.de\/en\/wp-json\/wp\/v2\/media?parent=9703"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.lesestunden.de\/en\/wp-json\/wp\/v2\/categories?post=9703"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.lesestunden.de\/en\/wp-json\/wp\/v2\/tags?post=9703"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}