AI NotebookLM Experiment: Analyzing Terry’s Poems


I vaguely remember signing up as a beta user for Google’s NotebookLM AI experiment but then forgot about it until an invite came in my email yesterday. It’s still a bit funky in its workings but the general idea is that it uses Google Bard, with up to 10 texts that you can upload or paste into its system for inquiry.

You can then do questions or analysis or creative activities across all the texts (or just some, if you decide to uncheck the texts), engaging in a sort of conversation with the various texts. (Honestly, I thought it was going to have more features and I believe it will, as what is there right now didn’t seem too revolutionary to me).

I tinkered a bit, and then thought: I’ve been enjoying reading the poems of my friend, Terry Elliott, so why not use his three most recent poems. I pulled them in, and began a session of interrogating his poetic texts. I explored theme.

Terry poems Themes

Then, I explored imagery and common phrasing and words.

Terry poems Imagery

I asked the Notebook to tell me what Terry hoped I was hearing in his poems. This was the most interesting part of my experiment, I think. It gathered phrasings and explained what it thought Terry was trying to say. I’m not sure how true it is but it gave me things to ponder, and forced me to look deeper at the poems (which is the whole point of what I was doing here — allowing technology to help me see the poems in a different slant).

Terry poems instructions to reader

I also turned each poem into a haiku (the results are just “meh” in my opinion).

**The following is a haiku translation of the first poem:**

**Future is dawning**
**Make poems to see it**
**Fete vos jeux**

**The following is a haiku translation of the second poem:**

**Alone with the trees**
**Be fluid and free**
**Let the leaf fall**

**The following is a haiku translation of the third poem:**

**Be a lighthouse**
**Sharing what you have found**
**Surprised by your mind**

I asked it to write a play skit, with a poet talking to the reader, and it came out robotic and just weird – no nuance. I asked it turn that play into another one, but with a pirate theme (with hat nod to Tellio of the Olden Days of CLMOOC) of a captain talking to a sailor, and the notebook just completely and utterly ignored Terry’s poems entirely. (The nerve!). I had it write a letter to Tellio, the poet, on the issue of dreaming and the future. It was fine, and very informal in tone.

I asked it to make a Cinquain, using words from all the poems, with TERRY as the letttering. Fail. But intriguing anyway as a small poem.


**Dawning future**
**Fluid, free, visceral**
**Making sense, redrawing maps**

I asked it to write a short essay, using the text of all three poems, on the topic of hopefulness, a theme it had identified across the poem collection.

**The Tree Poems: A Source of Hope**

The two tree poems that we have read, “Imagine Your Future” and “What It Takes More or Less,” offer a source of hope in the face of uncertainty. The poet’s message is that we can find hope in the natural world, and that by connecting with nature, we can find the strength to face whatever challenges come our way.

In “Imagine Your Future,” the poet writes about the importance of dreaming and creating. She encourages us to “make and make and make” our own futures, and to trust that our efforts will be rewarded. This poem is a reminder that we are not powerless to create our own destiny. We can make a difference in the world, and we can build a better future for ourselves and for our children.

In “What It Takes More or Less,” the poet writes about the importance of being present in the moment. She encourages us to “be alone with the trees” and to “be visceral.” This poem is a reminder that we need to take time to appreciate the beauty of nature and to connect with our surroundings. When we are present in the moment, we are less likely to worry about the future or to dwell on the past. We can simply enjoy the present moment, and find peace and happiness in the natural world.

The tree poems offer a source of hope because they remind us that we are not alone. We are connected to the natural world, and we can find strength and inspiration in nature. When we are faced with challenges, we can find comfort in the knowledge that we are not alone. We can find hope in the beauty of nature, and we can find the strength to face whatever challenges come our way.

I could go on.

It’s imperfect, as Generative AI often still is, but the ability to engage with multiple texts in one place (one notebook) has a lot of potential, perhaps. A significant drawback (for now, in beta) was that it didn’t seem to have save my work from session to session (I am sure that will get fixed). But I also noticed at one point that is stopped using one of Terry’s poems in responses to my questions.

Peace (in explorations),

PS — Terry gave me permission to share this AI work on his poems

Using Padlet’s New AI Art Feature

Golden Lines with AI Art

Padlet, which I use a lot with my students for sharing across classes, recently added an AI Art tool — with a tool name that I don’t really like (“I Can’t Draw”). As you might expect, my sixth graders are quite fascinated by it but I want them to use it to complement their writing and sharing, and not just turn them loose on it.

So, as part of a larger short story unit, I introduced the idea of Golden Lines — a sentence or two or phrasing from their stories that have some importance to the narrative, and then suggested they use the AI Art tool to make art based on their Golden Lines.

They are coming out pretty interesting, I’d say, and a little later in the year, we’ll do some explorations to deconstruct how the tool works and more. For now, it’s another tool for making complimentary art for their writing.

Peace (inked out),

Design A New Yorker Mag Cover: AI Issue

New Yorker Cover Design

The cover of this week’s AI-themed New Yorker magazine (I have not yet even cracked it open but will soon) included an invitation to design a new art cover for the magazine. I followed the link and had some fun (see above) . You can, too.

Peace (and Art),

The Beatles Final Collaboration (Thanks To Machine Learning)

I remembering reading something about Paul McCartney saying there was one more Beatles song under production, now that the Age of Artificial Intelligence was here, and to be frank, I thought: oh no. Please don’t let it be John Lennon AI Voice singing in the mix. Please don’t let it be AI George Harrison guitar.

It isn’t.

Instead, as I learned when I watched this short documentary last night, it’s a song that Paul, Ringo and George tried to work on decades ago to honor Lennon, with permission of his family, but the rough tracks that Lennon had recorded for a song that he never finished were distorted with loud piano and soft voice.

They gave up in the early 1990s. But now that Machine Learning is here and film director Peter Jackson has the technical skills, Paul realized, the computer algorithms and power could isolate Lennon’s voice and separate it from the rough mix that Lennon had made, and once the voice was isolated, they could build a song around it.

Harrison passed away in the meantime, so along with Lennon’s voice, Harrison’s slide guitar leads were also added into the recording, with McCartney and Ringo Starr playing along, allowing the claim that this is the Last Beatles’ Song to be true, such as it goes.

The song gets released today (Nov2), I believe. The documentary is worth a look.

Peace (and Sound),

Digital AI Oracle:The Prophecy Machine

Digital Oracle Prophecy Machine

I am teaching The Lightning Thief with my sixth graders and we are at a chapter where Percy Jackson gets his prophecy from the Oracle. I had this idea of finding an online site that could spit out age-appropriate prophecies for my students as an activity. I found nothing and then thought, why not make my own?

I knew the Flippity site had a spinner tool and I knew I wanted at least 50 prophecies so each student in each class could get two different prophecies. But … writing 50 prophecies, myself, in one night? Yikes. Not gonna happen.

Wait … I thought … what about ChatGPT?

Why not make it do the work for me?


It worked.

I had ChatGPT create 70 different prophecies, age appropriate for sixth graders, popped the phrases into the spinner, and yesterday, it was a huge hit with the students.

I described the spinner as our Digital Oracle, after a lesson on Apollo and the Oracle of Delphi, and the ChatGPT mix of prophecies were fun and interesting, with some having obscure Greek references for my students to wonder about. The mix of fantasy, mythology and positive thinking made for an enlightened time.

Thanks, AI.

Peace (spinning it),

Resource: Gathering AI Tools Across The Curriculum

AI Tools Across The Curriculum

A few weeks ago, I helped co-facilitate a session about AI in education, and for that session, we developed a resource that might be helpful to others, as it is built around different areas of the curriculum and content.

You can download the digital handout we created for participants of our session. We’ve grouped AI tools by curricular area and then broke out some other assorted resources that we think may be valuable for explorations.

View/download AI Tools Across The Curriculum resource

Peace (and sharing),

Generative AI and the Writing Classroom: WMWP Workshop

AI WMWP AnswerGarden Opening

Last night, a colleague and I facilitated a fascinating discussion and workshop about the impact of Generative AI in the writing classroom. It was the first Western Massachusetts Writing Project event at our new university home — we move from the University of Massachusetts to Westfield State University – and I designed and led the session with Catherine S., who runs the Writing Center at WSU.

The screenshot of the Answer Garden was a “writing into the session” activity, just to get a sense of where people were in their thinking of AI at the start.

One thing that made this session rather unique, I think, is the mix of educators — it was pretty even gathering of K-12 teachers (mostly, high school) and professors from the university, and that mix led to some deep, connected discussions about writing across the upper grades into the entry to college, and how platforms like ChatGPT, Google Bard and others are making an impact on the teaching of writing, and the writing that students are doing.

AI WMWP Group Activity

One activity that was a hit involved mixing the tables up with different people, so that college and K-12 folks did it together, and they were given a board with a span of “acceptable use of AI” to “unacceptable use of AI” with little cut-out squares that they had to place along that spectrum. Each square — such as using AI for brainstorming or Using AI to write a draft of a paper — sparked fascinating back and forth between participants about expectations of AI and their writers. (You can have access to make a copy, too)

AI WMWP Resources

We also created a large database of various AI platforms that could be useful for educators, grouping platforms and tools under curricular themes. We ran out of time for participants to play around with the sites, but made sure they had access to it. (You can have access, too).

Overall, our intentional message was not “the world is ending so ban AI” but more, “this is our new reality, so how can we start to think of AI as a partner to help us as teachers and maybe help our students as writers?” and I think that theme really resonated with the educators who joined us last night.

Peace (Writing It Down),

Magic School AI: Using AI To Resist AI

AI Resistance

A colleague, knowing I am interested in the emergence of Generative AI and its impact on teaching and learning, pointed me to MagicSchoolAI, a free (as of now) platform of tools for teachers. I spent some time with it, and I found it worth a look, with a wide range of tools under one roof that could be helpful to educators. (Note: I am not affiliated with the site at all. These views are my own.)

I used a tool within MagicSchool that generates questions for students watching a YouTube video (as long as the video is close-captioned) and I found the questions to be pretty thoughtful. I used the Teacher Joke generator and thought it needs some work (ahem). I used the Colleague Song generator to write a song about my fellow teacher friend, and it was very ChatGPT-ish in its construction (as in, fun to read, but not necessarily all that creative). I used the assignment rubric creator, and its final suggestions were pretty strong and useful, and something I could adapt for the real assignment I plugged in to try it out with.

One tool that really interested me, though, was “AI Resistant Assignment Suggestions” – in which you plug in assignment questions that you worry could be easily responded to by Generative AI (ie, cheating by students) and the site amps the question up in complexity and task, and then, helpfully, explains how its suggestions could help thwart an easily-made response from Generative AI. I found the results useful, actually, and its suggestions made me ponder more about the assignment I fed it (about protagonists and antagonists in stories).

Peace (Explorations),

WMWP Workshop: Writing In The Age Of Artificial Intelligence

Writing in the Age of AI 2023 - 1

I am helping to co-facilitate a workshop session next month on the teaching of writing in the time of Generative AI, and we hope to gather together K-12 educators and university professors to discuss the changing landscape, and collaborate on paths forward.

If you teach in Western Massachusetts, we invite you to attend. We scheduled it the day before the National Day On Writing, purposefully, so that we would remind ourselves of the human aspects of writing, even with the influx of algorithms and chat generators.

Peace (with technology),

Generative AI Presentation 3: Ethics, Policies and Reaching All Students

I did one final summer workshop presentation about the rise of Generative AI and the impact on schools. This one, like my last presentation, was with a group of school librarians, who were doing a week-long professional development around reaching all students, including those with disabilities.

My themes for this presentation centered first on the ethical considerations of using AI like ChatGPT and Bard, and then moved into how to begin thinking of school/classroom/libraries policies for students, and then ended with some ways that new AI-themed tools could help educators support students with some disabilities. I then provided a wide range of resources for them to explore and consider. (By the way, Eric Curts has done an amazing job in this area of inquiry, gathering resources on this topic.)

This is the third workshop I have given this summer (first with teachers in the Western Massachusetts Writing Project and then with another group of school librarians), and interest in all three has been very high by participants. We’re all wondering how AI is changing the educational landscape, and how we can adapt to meet the moment. Even for educators whose students are too young for ChatGPT or other tools, the interest is there to learn more.

I’ve tried to balance the concerns we all have with an open mind to the possibilities the AI might bring to the classroom. Threading that needle in these conversations can be tricky, but mostly, I have found, when educators learn more through discussion and explorations, the more open they are to considering the possibilities along with any pitfalls.

Our Western Massachusetts Writing Project is starting to plan a gathering of educators in the fall to do more of this work around AI, and I am likely facilitating part of that discussion with a professor from Westfield State University, our new home for WMWP.

Peace (and purpose),