This week, we finalized the project and reviewed the information in the presentation slides . We added the tag line for the project: “an interactive dictionary of common lunfardo terms in contemporary use in Argentina”.

Aaron added the last pictures to the commentaries and started to refine minor details across the site to ensure consistency in how each page is presented.

I reached out to two professors and received valuable feedback. They suggested moving key sections, such as definition, methodology and objectives, closer to the top of the page, directly under the title, to improve visibility. They also recommended incorporating English translations for difficult parts of the narratives to enhance clarity. We can possibly do this via tooltips as we did with the word “afanar”. I found these suggestions very useful and positive. But most importantly, I felt encouraged by the level of interest the site has generated. One of my colleagues mentioned she can use if in her class of Conversation where they study the variety of the language and registers.

In the coming days, we will begin revising the site to improve the final product. But for now, we are ready for the presentation!

As we approach our project launch, things are really coming together! We’ve been finalizing written content for our website and working through some visual glitches. Huge shoutout to Truly for getting to the bottom of the main issue and resolving it. You can check out the site in its current state here. 

The general layout is in place, and we’ll update the website with our final edits this week. Also, a huge shoutout to Michael, who has done a great job finding images for all of our close reads. Those will be implemented in the next website update as well. That being said, this week Truly will handle any remaining website tweaks and update the written content; Michael will start the white paper draft; and I will revise the presentation slides and prep for the rehearsal and final presentation. The team is maintaining continued communication via Discord during these final phases.

Nonetheless, we are happy to say that everything is on track for a hopefully smooth project launch. Throughout the semester, we’ve been taking turns writing these group updates, and I’m just now realizing I am writing the very last one. A bittersweet moment, for me. Thank you all for being a part of our journey, and for sharing yours with us as well. Excited to see it all come together at the GC Digital Showcase!

Excitement and anxiety are definitely rising as we close in on the final stages of this project. I might just be speaking for myself, but I have a feeling my teammates relate: As the time arrived where we would have to write out new prompts and actually produce the dataset, arguably the marquee feature of the AI Hallucinations project, we suddenly found ourselves oh-so-preoccupied with other things: Setting up appointments with the digital fellow and other advisors, adding to and refining the website, double-checking our archives and prompt-writing guidelines.

Reality had its own plans: The original plan was to each write about 15 prompts based on archival research on the Puerto Rican and Diasporican histories, query the models, and collect the data and then repeat the process for an aimed total of 100 prompt responses. But in the class before last, Sasha suggested we slash the size of the new dataset in half, so that we only write 15 prompts each for an aimed total of 50 responses. We were so focused on refining our fact-checking process and prompt-writing criteria that we soon realized we did not have enough time to break up the prompting process into two stages like we had originally planned.

Turns out, writing the prompts took up more time than any of us had originally expected. On Friday afternoon, we met at the main branch of the Brooklyn Public Library, with varying degrees of springtime allergies. None of us had finished writing our allotted prompts, as planned, so the first hour of our session was dedicated to finishing up that work together. Sasha and I finished writing our prompts quick enough that Sasha was able to walk me through prompting the models and organizing the output. We did not have time to fact-check any of the outputs together. So we spent the last 20 minutes of our time together reorganizing our schedule and priorities for the coming week.

Since we are further along on the website development side, we reprioritized as follows: We will each fact-check our own model outputs individually during the week, and come together to trouble-shoot in class. The other half of our time in class will be dedicated to making some final decisions regarding our web-hosting and domain because GoDaddy hates us. This is fact-checking week in more ways than one, as on Friday, we also confirmed two meetings with advisors: One with the Digital Fellow and another with Luke Walzer, both of whom have expressed an interest in going over our fact-checking procedures and methodologies. These meetings and our response fact-checking efforts during the week, should put us in a good position to start concluding the fact-checking phase of the project. After this coming week, we will focus on finalizing the website and preparing our materials for sharing and launch. 

We continued this week with both a presentation on our project and the work of collecting and entering Lunfardo terms. The presentation was an opportunity to think about how to communicate the project to our classmates and, ultimately, other DHers at large. With the feedback from that experience we will adjust the presentation in preparation for the showcase at the end of the semester.

As for the substantive work, some discussion about a couple of the terms prompted a rethinking of the inclusion of a couple of the terms. We are trying to focus on terms that are in wide use today. Since the language developed from the late 19th and early 20th centuries, at least some of the words, though appearing in tangos and movies, have fallen out of favor. This just goes to show that even with a narrow scope and well defined goals, we can still encounter surprises along the way! But this is also not a serious setback, and we are still on track to complete the text entry by the end of the course.

Over the next week, our goal is to ensure every term has a page conveying the same kind of information and affording the same kind of interaction, after which we can commence the remaining copy editing and other revisions.

I’m happy to report that we are on track for this project! By “on track” I don’t mean that we’ve followed our initial work plan exactly- that almost never happens. Even the best plans don’t perfectly survive contact with the chaos of reality. But we have hit our milestones in that we’re pretty much at the point in the process now that we thought we’d be at. The focus of this coming week, in our work plan, was on debugging the website and refining the written materials. This is still basically our plan for this week- revising each other’s close readings, putting together final versions of the user facing text around the data visualizations, and adding a few final pieces to the site, as well as fixing bugs. We might even start revising the presentation this week if there’s time – if not, that’s out focus the next couple of weeks!

How we got here is a little different than how we expected, though. When we initially made our work plan, the close readings were just an idea for a potential add-on, so we didn’t explicitly include them in the plan. But as time went on, they became more of a core part of the project, and some time that we initially thought would be spent refining the visualizations went to working on those. We also shifted around some of the work between us, which I think was valuable, since it gave us all a chance to try out some different tasks, and not get too stuck banging our heads against the same things again and again.

Overall, we’re at a good place, and not only that, it’s around the place we planned to be at this point! I’m excited as we enter the final stretch, and I’m very confident in our group to bring this project home and make something interesting and valuable.

This week, we made significant progress on our project. I revised the start page to clarify for the user not only what “lunfardo” is, but also what they can expect when clicking on the available terms and how to navigate the site. I made the language of this section simpler, adapted for students of intermediate level. I explained that they could choose any term based on their personal interest since there is no specific order to follow. By doing so, they would be able to listen to tango songs that show the historical use of each term, along with more recent examples to see its evolution. And then I invited them to start the journey and try the activities.

Aaron added a link to our personal blogs with the idea of offering users more insight into the project’s development and the thought process behind our choices. This would allow users to understand more the ideas behind the decoration and the logo (what “filete porteño” is and the suggestions implied in the “Milonga” font).

I am currently adding more terms. Also, for all terms, I am adding a line that explains the most common use of each term in Argentina and an example of a common phrase that can be heard there. This should help users see the term in context. We also discussed the idea of incorporating audio, so that users can hear a native speaker pronounce the phrases in Spanish. This would enhance the learning experience and provide a more authentic touch.

Aaron is currently working on the slides for the presentation, and I will continue adding more terms to complete the list by the end of next week. Our goal is to have everything ready for the final stages of the project.

Quick team update on where things stand since we got back from break.

Christian tracked down new links to digital archives focused on Puerto Rican histories. Finding sources that are both substantive and actually accessible is harder than it sounds, since a lot of digitized collections are fragmented or behind access walls. Having a solid list to work from is a real step forward for the prompt-writing phase.

Michelle has been working on two things. First, bringing in new design ideas for the website’s visual direction, and second, continuing to pursue outreach for project consultation. The design conversations in particular are starting to shape what the archive will actually feel like to someone encountering it for the first time.

A few bigger updates on the project overall. We’ve finalized our domain and are in the process of purchasing it and securing hosting, so the project will have a permanent home on the web soon.

We’re also scaling back the Puerto Rican history dataset. Given where we are in the semester, it’ll come in at roughly half the size of the BKED dataset. It’s the practical call, since a smaller, well-verified dataset is more useful than a larger one we don’t have time to fact-check thoroughly.

On the development side, we’re planning to add visualizations that compare hallucination patterns across both datasets. That’s the piece we’re looking forward to, since the comparative view is really where the project’s argument starts to become visible.

Coming up, we’ll also be putting together a first draft of the project slide deck, which will give us a chance to step back and think about how we’re telling the story of this project as a whole.

Individual and collaborative efforts within the past month have set everyone up to curate the data needed to fulfill core objectives while advancing the AI “Hallucinations” Project in other foundational ways. The website draft, presenting the BEKD as well as methodologies for constructing “hallucination” data, provides a base for designing an interactive, and appealing platform. Additionally, Michelle’s outreach form successfully enabled Sasha to begin finding initial audiences at Open Data Week. 

With these accomplishments in mind, we still have a few tasks to complete between today and the beginning of spring break. One of them is scheduling an appointment with a GCDI fellow, in which Michelle will soon find a time that is realistic for everyone, even if Spring Break permits. Lastly, I plan to assign Sasha and Michelle each to at least 2 of the digital libraries and databases already listed in the google doc. In doing so, each group member will have a set of digital locations to visit in order to begin conducting some research, which would be helpful with making ideas for prompts. The query prompts, as we have established, will inquire Puerto Rican histories, therefore some research ahead of time will benefit the overall pacing. In addition to post-Spring Break tasks, Michelle will finalize the website’s domain name. On that note, the project is in a solid position, where progress is certain after this point. The developmental successes made in this month have set the foundations for completing core objectives, such as writing up the prompts. Especially considering that I recently made guidelines for prompt engineering, it is further evidence that the AI “Hallucinations” Project has the tools and overall means to curate and share details of generative hallucinations to academia.

The first phase of our work plan ended yesterday, March 26. During the first phase, the team met on Wednesdays in one-hour long Zoom meetings, as agreed. The group finalized the system selection and completed the compilation of terms, as planned. Aaron procured the domain and hosting, which later had to be moved to a cheaper plan, and he installed and configured the system, which leverages DokuWiki to provide robust and low compute content management. Aaron prepared a preliminary interface design, as planned.  He also managed to include some beautiful decorations in the style of “filete porteño” and also he included the colors of Argentinian flag and a beautiful font very appropriate for the site called Milonga. 

Natalia started to write the narrative of the first term “afanar”. We were supposed to have the narratives for all terms at this point (we  are behind in this respect). At the weekly Zoom meetings, the team discussed the progress on the interface and the narrative of the first term. The group also discussed how to add interactivity via DokuWiki plugins  for the quiz section. They also added explanations of some of the lunfardo terms included in the narrative section. This is very useful since it helps clarify the meaning of some difficult words that may appear. The group also started conducting initial outreach and contacted people that could spread the project among Spanish instructors and students. 

I think that the group met the expectations for this first phase. Even if the team should have by now all narratives already written, the compilation of examples and links has been finished, and I am sure that the group can complete both the narration of the commentaries and the entry of all the elements in the pages during the second phase (from today to April 16). This is the plan for the Spring break. In addition, Natalia will be designing the interactive activities for the remaining terms, while Aaron will be spending time drawing our logo, refining the design of the pages, and trying different forms of interactivity.  Overall, everything looks good; our goals have been fulfilled, even if the coming weeks will be fundamental to get closer to the completion of our project.