The machine lets you quickly knit either circular tubes or flat panels, and I found it surprisingly easy to use as someone who doesn’t know anything about knitting. The main thing I learned is you need to be careful about how much tension you put on the yarn as it goes into the machine, and you also need to watch carefully at each end or you risk dropping stitches. I dropped a few and had to fix them later, which I will show in a minute.
Whenever we help someone in Makerspace we make a tick on a piece of paper under the appropriate technology. These are called “Reference Interaction” and each tick is one interaction, not one question: if you ask 3 questions all at once we record that as one tick, and if you later ask another question we record that as another tick. This is all entered into a system that records the library’s stats. We have had over 10,000 of these interactions in the Makerspace since we opened!
The spreadsheet I used to calculate the number of rows I would need to represent the data
To turn this data into a scarf, I did a little experimental knitting until I figured out it took about 8 rows to make an inch. Since I knew I wanted something around 30 inches long, I played with the data until I figured out that if each row represented 300 interactions, I would get a scarf that was 33 inches long. I set up a spreadsheet to calculate this and added a colour, order, and “knit to” column which would tell me when to stop and change yarns. I then riffled through our new yarns in our community fabric stash until I found enough contrasting colours made of low-quality material to make the project.
The knitting machine in action!
Then I started knitting! I used the row counter until I got to the right number, then cut the yarn and tied it to the next colour. This is another place where it’s easy to make a mistake, and a couple of times the yarn came untied or risked getting stuck in the machine. It pays here to go slow and learn how to tie a tight knot. In total, it required 269 rows and I estimate it took about 2 hours in total to make.
As I said, I dropped a few stitches so I googled around a bit and found that many people just take a new piece of yarn, loop through the dropped stitch and weave the ends back through the finished piece to hold it in place. I did that, badly, using a contrasting colour that would show my work. My theory is it’s always good to show when you make mistakes, especially when you run a Makerspace and ask people to try new things. Luckily, I make plenty of mistakes.
The fix for the drop stitches
And here is the finished project! It will be hanging in the Makerspace until it gets cold enough one of us takes it down to wear it, so check it out next time you are here. I’d love to see people using the new knitting machine for all sorts of projects, as well as people experimenting with data physicalization and other kinds of data visualization. If you have questions or ideas, let us know or come by one of our co-working sessions.
Weeknotes are a habit I’m cultivating where I share what I’m working on or thinking about, primarily in my professional life, without worrying too much about the ideas being full-formed.
thinking about / working on:
Show Up & Make
I’ve rebranded the Makerspace co-working sessions (which are also my sort-of office hours) from “Makerspace Sandbox Sessions” to “Show Up & Make” so the idea is easier to understand. This name also aligns with a long-running program called Show Up & Write that the library runs with our centre for teaching and learning, which is nice since I am now also collaborating on this project with Alexis Brown, a faculty member from CELT.
It’s only the second week and I’ve already done 3 of these sessions. People are coming! Not many yet, just 2-3 each sessions, but it’s a start. Most interestingly, students have come who have never been to the Makerspace before, and they are coming not with projects or ideas, but with questions about what they can use the makerspace for and how. This is excellent but unexpected: these events were designed for people with ongoing projects or questions.
This is yet another example of something I learn again and again: there are many people who need permission to come into unfamiliar spaces, and events provide that permission.
Attention as pedagogy / Attention as love
For a long time, I’ve been thinking about how attention is the most valuable resource I can offer. Sure, I have some expertise in some areas, but even where I have something useful to share the prerequisite is still paying enough attention to know how I can help (see: reference interviews).
I increasingly find the thing students most want from me is my attention. They don’t really want to explain an idea to me so I can help them than they want to explain an idea to me so they can see how that idea fits into their emerging sense of self; I provide a mirror for them to explore their own emerging sense of self and knowledge. The worst thing I can do is step all over that process by taking up all the space.
What I can do is be interested. I can give them my attention. And sometimes I might be able to give them some advice or suggest they think about something else.
A very common trope is to treat LLMs as if they were intelligent agents going out in the world and doing things. That’s just a category mistake. ==A much better way of thinking about them is as a technology that allows humans to access information from many other humans and use that information to make decisions==. We have been doing this for as long as we’ve been human. Language itself you could think of as a means that allows this. So are writing and the internet. These are all ways that we get information from other people. Similarly, LLMs give us a very effective way of accessing information from other humans. Rather than go out, explore the world, and draw conclusions, as humans do, LLMs statistically summarize the information humans put onto the web.
In short, they are distinguished by the sort of engagement they elicit from those who take them up. ==In Borgmann’s view devices are characterized by how they combine a heightened availability of the commodity they offer with a machinery that is increasingly hidden from view. Basically, they make things easier while simultaneously making them harder to understand.== Devices excel at making what they offer “instantaneous, ubiquitous, safe, and easy.”
Focal things, not so much. ==Focal things ask something of you. Borgmann speaks of their having a commanding presence. They don’t easily yield to our desire for ease and convenience. A radio and a musical instrument both produce music, but only one asks something of you in return.==
One way to spot people who are good at solving poorly defined problems is to look for people who feel good about their lives; “how do I live a life I like” is a humdinger of a poorly defined problem. The rules aren’t stable: what makes you happy may make me miserable. The boundaries aren’t clear: literally anything I do could make me more happy or less happy. The problems are not repeatable: what made me happy when I was 21 may not make me happy when I’m 31. Nobody else can be completely sure whether I’m happy or not, and sometimes I’m not even sure. In fact, some people might claim that I’m not really happy, no matter what I say, unless I accept Jesus into my heart or reach nirvana or fall in love—if I think I’m happy before all that, I’m simply mistaken about what happiness is!
All this has happened very quickly, which may make it seem like we’re careening toward a “general” artificial intelligence that can do all the things humans can. But if you split problems into well-defined and poorly defined, you’ll notice that all of AI’s progress has been on defined problems. That’s what artificial intelligence does. In order to get AI to solve a problem, we have to give it data to learn from, and picking that data requires defining the problem.
Weeknotes are a habit I'm cultivating where I share what I'm working on or thinking about, primarily in my professional life, without worrying too much about the ideas being full-formed.
thinking about / working on:
A new term begins today, along with a bunch of new and old programming. This morning over coffee while reading the newsletter Dense Discovery the author Grace Burrowes posed the question “What problems are we trying to solve?” as a question worth asking, and I thought I would use it here for what I am working on this week.
How do we support users who want to experiment with computer and electronics prototyping in our existing space without changing our access model?
This week I am meeting with a group of faculty, students, and lab technicians to talk about how to turn one of our rooms into a space for computer and electronics prototyping. This has been an under-explored area since we opened almost 3 years ago because it’s hard to do within the space and expertise we have, and also because there’s ways it could break our current access model of “everyone can walk in and use everything within 2 minutes.”
How do we craft a position description that meets our department’s immediate and future needs while combining experience real candidates actually have into a job that someone could successfully do?
We recently failed a job search, and so we need to re-think what we are expecting. There are, as always, constraints, but we have some room to try to make the position better and more likely to be successful.
How can we provide computing power to users for exploring AI within an open lab environment?
This isn’t mine directly, but something happening I’m being asked my thoughts about, and which I care about a lot since we really need a better teaching lab for the Makerspace. I am leaning towards wanting a space that has enough compute to run basic local models, but nothing so fancy or specific it can’t be used for things like 3D modeling, video editing, etc.
How can we provide introductory workshops for the users who need the permission a workshop gives them to come into the Makerapace, without becoming a teaching space?
When we opened I didn’t want to teach any workshops. Last year I did a few and they quickly filled up. People clearly need the permission a workshop provides, even if they know that we will literally just be making them do the tutorial that is on our website and they could do anytime. I’m still working on finding a balance here, both pedagogically and for my own workload, but I suspect I will do more of these this semester, including a new workshop on AI.
Weeknotes are a habit I'm cultivating where I share what I'm working on or thinking about, primarily in my professional life, without worrying too much about the ideas being full-formed.
quotes
We’ve all seen beautiful pictures from Midjourney, presently the undisputed leader among several image-generating programs. It appears the LLMs are a lot more adept at generating visual art than text. But are they really? Artists and software engineers will both tell you they’re far from perfect. Even those images that do not have obvious issues, such as too many fingers on a character’s hand or a building melting into the ground, may still suffer from poor perspective, characters staring into nothing, and other such imperfections. As explained by AR/VR engineer and award-winning author Kimberly Unger, “More people have a grounding in the structure of language, even though they may have forgot the specifics, then have a grounding in the structure of visuals. So to your average observer, it’s easier for them to understand, often unconsciously, where the text goes wrong, than it is for them to understand where the pictures go wrong.” (View Highlight)
It’s the last week before the term begins and I’m heading into the mountains with my partner for a few days this week to recharge before all the wonderful craziness of September starts. Hopefully this will also be a nice way to end what has been an unexpectedly busy and stressful summer, during which my mom passes away after a short illness with cancer.
We’re leaving Tuesday afternoon, so this week is mostly about making sure the Makerspace team is set for the week, my new Student Ambassadors have their schedules, and I’m ready for their training day in two weeks. But I’ve also existed in post-secondary long enough that my real year is September to April, so it’s a good time to think about priorities for the year.
Makerspace:
Spend more time with users
Encourage user projects that go deeper and wider
Focus on our finding ways to make our values concrete
Department Chair:
Survive as solo chair until January when my co-chair returns
Professional Development
Finally finish my sections of the paper we are writing about a makerspace assessment project from almost 2 years ago (yikes!)
Find potential site-visits for my sabbatical next July, focusing on people and institutions using making (broadly defined) to rehabilitate our relationship with the more-than-human world
How I’m going to do these?
Makerspace Sandbox Sessions: weekly co-working sessions where people can come work on projects in a supportive, collaborative environment.
Training our student ambassadors to help users to be more sustainable and to try new things
Scheduling dedicated time for chair work and trying to most box that work into those times
Scheduling dedicated time for professional development
photos
Some wonderful slime molds from Tod Mountain at Sun Peaks
links
Jason Edward Lewis on Making Kin with the Machines [[_reference/Readwise/Making Kin with the Machines – Jason Edward Lewis – articles – annotations.md#^9iia1w|*]]
My grandfather, Standing Cloud (Bill Stover), communicates Lakota ethics and ontology through speaking about the interiority of stones: “These ancestors that I have in my hand are going to speak through me so that you will understand the things that they see happening in this world and the things that they know [. . .] to help all people.”24 Stones are considered ancestors, stones actively speak, stones speak through and to humans, stones see and know. Most importantly, stones want to help. The agency of stones connects directly to the question of AI, as AI is formed from not only code, but from materials of the earth. To remove the concept of AI from its materiality is to sever this connection. Forming a relationship to AI, we form a relationship to the mines and the stones. Relations with AI are therefore relations with exploited resources. If we are able to approach this relationship ethically, we must reconsider the ontological status of each of the parts which contribute to AI, all the way back to the mines from which our technology’s material resources emerge.
and
Hāloa, the long breath providing sustenance to us all teaches us to maintain pono relationships; wahkohtawin, being in relationship with others; wakȟáŋ, that which cannot be understood. These are three concepts that suggest possible ways forward as we consider drawing AI into our circle of relationships. They illuminate the full scale of relationships that sustain us, provide guidance on recognizing non-human beings and building relationships with them founded on respect and reciprocity, and suggest how we can to attend to those relationships in the face of ineffable complexity.
In going about my work, it became apparent that as “library faculty” I had none of the protections of the state staff contract, and none of the flexibility of the tenured or tenure-track faculty contract. None of my colleagues with faculty status in the library did. Faculty status, however precarious, was our means to getting on campus committees. It was how we qualified to apply for on-campus grants to do research and pedagogical projects.
Weeknotes are a habit I'm cultivating where I share what I'm working on or thinking about, primarily in my professional life, without worrying too much about the ideas being full-formed.
quotes
“There are moments when you just need to go with the flow (intensive teaching with a fixed schedule, grant application deadlines, etc). But there are also moments where you can claim some time back and use it for something very valuable: reconnecting with your work. Finding what makes you tick, what you care about in your work, what brings you most satisfaction. Figuring out where you can really make a difference with your skills, passion and personality.”
Last week we got a knitting machine in the Makerspace, inspired by Quinn Dombrowki’s excellent post about using knitting machines for data visualization Knot Hard: Accessible Textile Data Visualization With a Circular Knitting Machine. While I motly don’t have time to use things in the Makerspace, I like at least try every new thing out before asking students or staff to do the same. I imagine myself like Hammond in Jurassic Park trying to get the velociraptor babies to imprint on him when they hatch.
I decided to visualize our reference stats, breaking then down by technology type, and going back to when we opened in March 2022. I did two tests just to see how the machine worked, then figured out about how many rows were in an inch and that 269 rows would make an acceptable scarf, which meant each row needed to be about 300 reference interactions. I also cut out a couple of categories like “computer prototyping” that I thought didn’t have enough interactions to work well aesthetically, though I wish now I hadn’t done that.
Category
Number of interctions
Inches
Lines
Colour
Order
Knit to row
Makerspace only: Tech Category
inches
lines
colour
VR
649
2.16
17.31
pink
7
214.59
Recording Room and Technology
523
1.74
13.95
white
2
45
Textiles/Wearables
593
1.98
15.81
light blue
4
89.81
3D Printing
3583
11.94
95.55
turquoise
5
185.36
Cricut
1170
3.90
31.20
green
1
31
Tour
1071
3.57
28.56
red
3
74
Other
2069
6.90
55.17
dark blue
8
269.76
Embroidery
447
1.49
11.92
orange
6
197.28
Here is the result! Not perfect, but not terrible!
Doing this also reminded me that I like this work. It was really nice to sit down for a couple of hours in our bright, positive space around staff and students working on their own projects. It reminded me that I love the space and culture we’ve built, and I like this work.
Last week I mentioned that I am developing weekly co-working and learning sessions for the Makerspace, which I am tentatively calling the Sandbox Series, in the hope of inspiring a sense of play without outcomes. Since then, I’ve developed the idea enough I can call it a program, created a website to share information, and scheduled the sessions to happen twice a week this term.
That’s an ambitious schedule, but I’m hoping I can make it work by thinking about these sessions less as stressful events I’m leading that take me away from my work and more like dedicated time to focus on parts of the work that I love, which is connecting with students and colleagues, helping them attain their goals, and exploring my own projects.
working on:
Onboarding new staff
Developing a new training schedule for student ambassadors
A grant to continue the Indigenization work we’ve been doing in the Makerspace, including sponsoring workshops and holding welcome events for Indigenous students.
Learning to quilt via 2 workshops hosted in the Makerspace that have been organized and taught by a couple of our Library Technitions.
Like many, I’ve been playing with LLMs over the past two years, and my own understanding of these technologies continues to evolve the more I use them. There are obviously many problems with these technologies and how so-called AI is being developed, implemented, and used, but it’s also been a long time since I’ve been as fascinated by a technology or as impacted by its use. They are deeply weird and unpredictable, both powerful and macabre.
LLMs as Perspective Simulacra Engines
One way I’ve been thinking about LLMs is as engines for simulating different perspectives. LLMs are mathematical models trained on huge amounts of content, much of it writing from different people’s perspectives. This data is represented as connections with different weights. People, especially at first, tend to use very generic prompts, so what they get back is influenced by the “heaviest” weights, which tend to be pretty average/mid/beige. As you learn to use more specific prompts and give it more context, you trigger “lighter” or “deeper” connections, which results in more unique, weird, and useful output.
Don’t take any of this as a technically accurate account of how LLMs work.
What I’m often doing is giving the LLM some original content (an idea, proposal, etc.) and trying to get it to simulate a specific perspective through both the prompt and the content. My partner says this is a very librarian way of thinking about LLMs: I’m kind of using them as a “library” of simulated perspectives that I can “retrieve” and apply to my work (superficially this is like a library, but it’s also clearly not at all like a library for there is nothing to collect, retrieve, or curate). For example, I’ve asked LLMs to ask me questions about a program I’m developing from the perspective of future attendees, and to review an idea from the perspective of someone passionate about our pedagogies or values. Prompts like this that are given along with well-formed original documents can be extremely powerful ways of rapidly testing and revising ideas.
There’s another way of seeing this metaphor.
LLMs as Frankensteinian Meat Sacks of Collected Neural Tissue
I recently finished “The Expert System’s Champion,” the second in a series by science fiction author Adrian Tchaikovsky. Tchaikovsky is very good at exploring what non-human sentience might be like, and his “Children of Time” series is particularly good in this respect. This book felt more mythic than his others, reminding me a little of Becky Chambers’ Robot and Monk series or Ursula Le Guin’s Earthsea series.
I won’t try to explain the whole plot, but the next two paragraphs do contain spoilers.
The book is set on a planet where colonization mostly failed due to a hostile biology. Generations later, what remains is something like medieval villages organized around engineered “hives” of “wasps” that pick individuals to fill roles like law-giver and doctor, burrowing into them, and turning them into “expert systems” that more-or-less take the person over to fulfill the role needed to manage the community. These wasps were one of the ways the original colonists managed to survive on the planet. All this has been forgotten and the people who live in the villages who have their own myths and understandings of these systems and the world they live in.
In this second book, the colonists encounter a species of giant snails with another sort of hive structure organized around a truly giant queen snail. This species survives by being capable of hybridizing with anything it encounters, integrating whatever it consumes into itself and the hive, including memories and, for lack of a better phrase, the ways of being of the thing it consumed. There was a splinter group of colonists who were consumed by these snails shortly after they arrived.
“There is nothing of us but Leviathan and her dreams,” uttered the thing called Geordi. “I told you. Before she took us, I told you. Whatever she swallows becomes her mind. Whatever she takes within herself becomes a dream in her, and though she is slumberous and insensate, those dreams can think for her and advise her and give her a mind and a purpose. And so she calls to the Children, our Children, in the voice we give her, and they act as her hands and haul her across the land. You stand within her, and so you will be her dreams soon enough, and perhaps you will guide her purpose when she dreams you.”
Adrian Tchaikovsky in “The Expert System’s Champion”
In this quote, we meet one of these colonists, entombed in the wall of the queen, “explaining” what it is like to be entombed in the queen and part of her mind. The scare quotes are because it’s clear the consumed colonists don’t live anymore, but rather have become part of the snails. It’s not at all clear if the snails themselves are “conscious” beyond the abilities they have from those they consumed.
This is another way of seeing LLMs: as giant meat sacks of neural tissues, harvested by a marauding evil doctor, spliced together and reanimated by the electrical sparks of your prompts.
I wish I could say all this was leading somewhere deeper than wanting to write that last paragraph.
Weeknotes are a habit I'm cultivating where I share what I'm working on or thinking about, primarily in my professional life, without worrying too much about the ideas being full-formed.
I’m doing a Monday weeknote this week since I haven’t done one in a couple months and I need to get back into the habit. This summer has been chaotic with lots of unexpected personal and professional challenges. The fall semester is in sight though and it feels good to be getting back into habits. No links or anything else this week.
Working on:
Makerspace Sandbox Sessions: These are going to be weekly or bi-weekly co-learning and working sessions where students, staff, and faculty can come work on their projects together. The idea is to kickstart more community engagement and collaboration and create a space for people to make progress towards their goals in a co-play situation. I have a pretty good idea of what this is going to look like now and so this week I need to figure out a schedule that is regular enough that it doesn’t feel random and flexible enough that people with a lot of different schedules can attend.
Collaborating with AI workshop: Part of our new Skill Share Series of short, active-learning focused workshops in the Makerspace where people can come explore tools and methods in a slightly more guided way. I did this last week for our staff PD day and parts of it went well (the local AI models are good enough and fast enough to be usable on our computers) and parts need to be reworked (more examples to get people started).,
Setting myself up for being successful as the only Department Chair this fall: My co-chair is on a 6-month sabbatical, so until December, I am both the full chair of our department and doing my normal Makerspace work. Chair work is a mix of ongoing responsibilities which can be planned for and dealing with the unexpected. If nothing else I need to make sure my systems are set up to deal with both.
Weeknotes are a habit I’m cultivating where I share writing (and some links) as a thinking-in-public process. The idea is to explore ideas I’m grappling with, primarily in my professional life, without worrying about them being full-formed. The potential visibility of these notes is a nudge to develop them a bit more than if they were private. While my audience is mostly theoretical, if you’re reading this, please understand these are meant to be exploratory and provisional.
Half a week late on this WeekNotes as I am still wrapping up loose threads from last term. One thread is a presentation the Makerspace team (including the technitions who work in the space) and our Assessment Librarian are giving next week at WILU on “Developing and Assessing a Culture of Change at the TRU Library Makerspace” It’s mostly done, but I need to finish my part about the emotional impact of working in a space built for change, so I’m going to brainstorm that here.
What is the good?
The Makerspace is definitely the most rewarding thing I’ve done professionally. Nothing else comes close.
Some of the reasons for this aren’t about how we are a culture of change: I work with a terrific team; we get to know our users really well and see them develop over time; for some students, we become a place of belonging; we help people explore things they’re passionate about; almost all of our users are engaged in our space; sometimes they change their plans because of the time they spend with us; we’re often able to help get them jobs and other opportunities.
What is emotionally impactful for me about being a culture of change?
One thing is that I’m always learning new things. We’re a growth focused learning space and so, in a way, our users’ growth makes us grow; as they learn something new about sewing or podcasting or 3D printing, often we do too. I love learning new things.
Another thing is that I am often surprised as some expectation or assumption is unsettled. Seeing that something I thought would be the case isn’t.
Which I guess is connected to the last thing, which it is that it is humbling in the best way. Seeing ideas or solutions I didn’t think of or couldn’t have done. Seeing that a staff member is really good at something they didn’t know they were good at; that they are better than I could be. That is very rewarding when you work together in a team.
What can be hard?
Trying new things takes a lot of time and energy. It can be exhausting. You need to be careful about boundaries and burn out. I am not good at that part.
Working with people who have ideas or want to get involved requires a lot of mentorship and mediation. Often a lot more than if you just did things yourself. Definitely more than if you just had a suggestion box.
Finally, not all ideas are great ideas and not every plan works out. You need to say no a lot, explain why ideas won’t work, or how they will break something fundamental to your mission or values.
The core problem of ElevenLabs—and the generative-AI revolution writ large—is that there is no way for this technology to exist and not be misused. Meta and OpenAI have built synthetic voice tools, too, but have so far declinedto make them broadly available. Their rationale: They aren’t yet sure how to unleash their products responsibly. As a start-up, though, ElevenLabs doesn’t have the luxury of time. “The time that we have to get ahead of the big players is short,” Staniszewski said. “If we don’t do it in the next two to three years, it’s going to be very hard to compete.” Despite the new safeguards, ElevenLabs’ name is probably going to show up in the news again as the election season wears on. There are simply too many motivated people constantly searching for ways to use these tools in strange, unexpected, even dangerous ways. (View Highlight)
At first, previously viral (but real) images were being run through image-to-image AI generators to create a variety of different but plausibly believable AI images. These images repeatedly went viral, and seemingly tricked real people into believing they were real. I was able to identify a handful of the “source” or “seed” images that formed the basis for this type of content. Over time, however, most AI images on Facebook have gotten a lot easier to identify as AI and a lot more bizarre. This is presumably happening because people will interact with the images anyway, or the people running these pages have realized they don’t need actual human interaction to go viral on Facebook.
Join award-winning writers and directors Daniel Kwan and Daniel Scheinert as they talk about the process of developing, creating, and releasing their surprise hit movie that took the world by st— okay, look, if you’re still reading this, we should tell you that we’ve run out of new things to say about Everything Everywhere All At Once, so although we’ll try our best to stay on topic, we’ll most likely go on a bunch of tangents about the state of the world, the impending climate crisis, the collapse of consensus truth, the rise of AI, the importance and impossibility of self care, and our collective responsibility as storytellers to confront the issues of our time, because that’s probably going to be what’s on our mind, but we can’t make any promises, but at times we don’t feel qualified to talk about any of that stuff, anyway we hope you enjoy our SXSW keynote!
Weeknotes are a habit I’m cultivating where I share writing (and some links) as a thinking-in-public process. The idea is to explore ideas I’m grappling with, primarily in my professional life, without worrying about them being full-formed. The potential visibility of these notes is a nudge to develop them a bit more than if they were private. While my audience is mostly theoretical, if you’re reading this, please understand these are meant to be exploratory and provisional.
quotes
“It is easy for me to imagine that the next great division of the world will be between people who wish to live as creatures and people who wish to live as machines.” – Wendel Berry, 2000, Life is a Miracle
thinking about
It’s the end of the academic term, which means many things require reports.
While I am beholden to write reports and sometimes even do them of my own volition, I’m not sure how often they’re read or have any impact, especially if they are required by some process but not by any actual person. I’m reminded of a colleague at a previous job who would joke that our annual performance reviews should take the form of a form filled out by both the employee and their manager that just had a checkbox for “I’m doing okay” and “you’re doing okay” and if everyone agrees everyone is doing okay, that would be the end of the review.
The one beneficial thing these reports could provide, honest assessment and reflection, is often lost by the need to be relentlessly positive, especially if your job or resources for your organization is at stake. Their format, usually formal and narrative, further obscures anything valuable they might contain.
All this makes them one of the things we do that AI is actually pretty good at, and I suspect a lot of us (me included) are using it for summarizing and drafting reports, if not for writing the whole thing. If done poorly, as it usually is, just further removes and obscures what is valuable.
I’d love to just a submit a shorthand “I’m okay, you’re okay” style report for many of these, but I suspect that wouldn’t go over well. But here is my shorthand “I’m okay, you’re okay” END OF THING REPORT for a couple of things I’ve written up recently.
Makerspace End of Term Report
I spent less time than I wanted in the space with students and staff, but more than last term. I am working on increasing this by getting out of other commitments, but this is taking time.
It feels a little less busy in the space this year, but I don’t think this is a problem (though we should probably do some formal assessment to find out). There are still a lot of people using the space, and more of those seem to be learning independently and working on intensive projects over longer periods of time. If true, I am not sure if this is due to a change in our users’ behaviour, a change in how we run the space, or both.
Trained staff who understand the vision and culture of the space remain essential to student success and we are losing two staff members this year, one to a promotion and one to pursue a master’s in library and information science. While it’s wonderful watching colleagues move on to their next thing, it does cause some uncertainty about the future.
Sustainability and Indigenization connect with many other values that we want to promote, such as equitable access, belonging, community, and critical making. They are multipliers for the rest of our values.
Sustainability Grant
I was far too ambitious when I wrote this grant. Present Frank always assumes future Frank will have more time than he currently has, which is never true.
We completed most of the concrete objectives but none of the stretch goals
Student workers bring energy, connections, perspectives but require a lot of time, probably as much time as doing most tasks yourself. it is still worth it to gain those perspectives and connections and provide mentorship.
I need to get better at delegating work
Coyote Grant
We did a lot in a short time, including hosting welcome events for Indigenous Students and sponsoring workshops on feather work, moccasin making, and beading.
We need to start earlier in the year, probably right away in September, if we expect to collaborate with student clubs on events as we wanted.
Indigenization is about relationships and community. Everything we do must be part of an ongoing connection.
Department Chair
There is most likely a joke about to be made along the lines of: “the first rule of being department chair is don’t talk about being department chair”
There are many problems in the world that are in the category “not big enough to deal with the consequences that will arise when dealing with them” and which are therefore left alone until they become big enough that it’s worth dealing with those consequences.
photos – Iridescent Circle of Clouds
I recently started playing Dungeons and Dragons with a group of friends and I’ve been playing around with using AI to teach me the rules and strategies. It works surprisingly well to give it your character sheet and some background story and then ask it questions over time about rules, spells, etc. It’s also a good way to learn how it’s memory works and when it breaks down.
Last night after we played I used the same chat to generate some images of the character. ChatGPT’s image generation now allows you to ask for specific edits to images and even parts of images. It’s definitely not perfect and to my amusement, no matter how many times I asked it to give me a baseball cap it remained convinced (for training data reasons I suspect) that gnomes wear pointy hats. I love this because this is exactly my partner’s preferred “toque on baseball cap” hat style.
I also asked it to write a bio in the style of a New Yorker profile. It’s not perfect, but this was it’s first draft and it’s pretty good:
“Iridescent Circle of Clouds,” a rock gnome Druid, recently emerged from decades of hermetic solitude in the desert, arrives in the world with a conviction as clear as it is radical: that all existence is conscious, nothing possessing more intrinsic value than anything else. This philosophical outlook, born from long contemplation and the harsh realities of the desert, flavors his every interaction with a curious blend of detachment and profound connection. Despite his austere background, he has cultivated a somewhat incongruous taste for the finer things—silk robes, aged bourbon, the cool draw of a well-crafted pipe—each a reminder of the sensory joys he once eschewed. As he navigates the bustling towns and verdant wilds beyond his sandy confines, “Iridescent” often seems to orbit the edge of solipsism, seeing the universe’s vast complexity as a mirror of his own consciousness. This true neutral character is constantly weaving his personal revelations into conversations, seeking his place in a world he regards as both an extension of self and a boundless mystery to be unraveled.
But I am going to say something that I mean sort seriously but not literally: I don’t really care about copyright! I don’t really care about paywalls! I’m okay with it if you only ever see my reporting via a chatbot! Copyright and paywalls are simply means to an end, and that end is the pursuit of human knowledge and self-liberation: the end is our freedom. And one of the principles of human freedom that I hold dear to my heart is that nobody should be providing labor to massively profitable corporations for free.
Sara Hendren on The City and the Limiting Virtues – This year we formalized our values and pedagogies into a program description and passed that through out faculty council. The main reason I decided to do this was because I think I’ve learned that its as important to know what you aren’t (in our case, we are not a classroom, a lab, or a print shop) as what you are, and this document clarified both. This article reminded me of that.
The library holds a gradation of the limiting virtues: a half-quiet first floor with new books, tables and chairs for afterschool tutoring, and the information desks for everyone — the neighborliness of a public institution’s front door. The second floor features enclosed meeting spaces for groups on a first-come, first serve basis, plus a really really quiet room for patrons wanting the moderation of all notifications off. The entire third floor is devoted to children — a beautiful raucous energy, with activity rooms, cozy nooks, and floor-to-ceiling windows on every side. A teen room in the old structure holds high-backed wing chairs and booths for semi-sedentary socializing, and a maker space occupies much of the basement. Things you can do and things you can’t, by design.
But what if, as Bennett suggests, the world is already enchanted and the real alchemy that summons the miracle of being is that fusion of time and care that we call attention?
Weeknotes are a habit I'm cultivating where I share writing (and some links) as a thinking-in-public process. The idea is to explore ideas I'm grappling with, primarily in my professional life, without worrying about them being full-formed. The potential visibility of these notes is a nudge to develop them a bit more than if they were private. While my audience is mostly theoretical, if you're reading this, please understand these are meant to be exploratory and provisional.
quote: Ursula K. Le Guin on fiction being one of the best ways of learning about other people
“Fiction as we currently think of it, the novel and short story as they have existed since the eighteenth century, offers one of the very best means of understanding people different from oneself, short of experience. Fiction is often really much more useful than lived experience; it takes much less time, costs nothing (from the library), and comes in a manageable, orderly form. You can understand it. Experience just steamrollers over you and you begin to see what happened only years and years later, if ever. Fiction is much better than reality at providing useful factual, psychological, and moral understanding.”
The Wave in the Mind: Talks and Essays on the Writer, the Reader, and the Imagination – Ursula K. Le Guin
thinking about: what I find interesting about the current generation of AIs
I’ve been playing with AI again because a few AI plugins for the note-taking app Obsidian reached the point where they seemed ready for prime time. These plugins (co-pilot and smart connections) let you chat with different models within Obsidian itself, use your own notes as context, and create embeddings from your notes (which I don’t fully understand, but seems to be a low-cost way to help the systems understand the context of each note and find connections between them). Both these plugins allow using local AI models, which is terrific, but honestly, I have been using them with OpenAIs ChatGPT and with Anthropic’s Claude via API.
Obsidian contains all my notes, draft documents, projects files, journal entries, etc. going back at least 3 years. It also has all my reading notes and highlights from almost 10 years of e-books, internet articles, websites, and academic PDFs. Basically, everything text that I write or consume ends up in Obsidian. I like that it is very fast, uses Markdown, and has a frighteningly passionate community of users and developers.
I hate the way most people are using AI, which seems to be having it generate content from chicken scratch. It’s generic and horribly enthusiastic. I increasingly get 3 paragraph emails from students that sound like they were written by a committee of cocaine fuelled project managers.
What I like about AI is the possibility of a tool I can use to take my own ideas, in all their poorly formed and idiosyncratic weirdness, and probe them from different (imagined, fake, weird) perspectives and/or remix them with other ideas and into new ideas, outcomes, and formats.
What I want from AI is an on-demand committee of cocaine-fuelled Franklins remixing and probing my ideas with me.
So for the last few weeks I’ve been using AI for this purpose. Among other things, I’ve used it to help plan a day-long design thinking event, prep for hiring new student ambassadors, and learn more about my Dungeons and Dragons character (I am part of my first ever campaign with some friends right now).
What have I found useful?
Being able to use one or more notes as context for feedback on another note:
Give me actionable ideas for improving an event plan based on my highlights from a book I read a year ago about event planning.
Use my therapy notes to predict issues I might have with a given project (lol, I knowwww… but its advice was frighteningly on point).
Asking for feedback from the perspective of different personas:
Give me actionable feedback about this plan from the perspective of an instructional designer, an event planner, and a design thinking expert.
Write a FAQ for someone attending this event who has never attended a design thinking event or similar activity, using the information in this plan for context.
Create draft advice for a first-year student applying for this job about what makes a successful application package.
Integrate ideas from different notes to find points of convergence or do other things:
Brainstorm ways that ideas from note 1 could be combined with note 2 (one of my favourite uses because it can get weird quick and that is the point)
Remixing ideas or documents into different combinations or forms
Using the project plan, create drafts of supplementary documents, including a guide for attendees, a facilitator guide, and a guide specifically for person X and Y.
(These examples aren’t the actual prompts I’ve used, which usually requires a lot of imagination and direction. I’ve found working with AI is more like writing the AI a story than it is like coding)
What this gives you isn’t immediately usable, instead you get a good idea or two, some inspiration, part of a paragraph, a few question/answer pairs, etc. You then need to edit those, integrate them into your document, and repeat the process.
Does this save time? Yes and no. It takes more time than doing nothing, which given time constraints and under-staffing is what would normally happen. It takes less time than doing these things manually.
Is this better than doing them manually or having another person do these things? Again, in my experience so far, yes and no. If I could have a world expert in event planning, design thinking, and instructional design next door to my office who would provide immediate and tailored feedback, that might be better. Sometimes it might be worse. For the remixing and idea generation, I’m not sure it would be better… would I ever ask someone to read through my therapy notes and use them to generate failure points for a project? Or iterate through connections between IDEA A and IDEA B when neither is connected or related to a current project? Probably not.
photo: spring flowers
links
I liked this article about why We Need to Rewild the Internet and applying an ecological metaphor to thinking about why the internet has become so terrible. It also had me thinking about the ways that all disciplines are increasingly “crisis disciplines” concerned with how we can save the things we love. I definitely thought a lot about academic institutions while reading this, and the ways we have been captured by the same forces threatening the internet.
“Ecologists have re-oriented their field as a “crisis discipline,” a field of study that’s not just about learning things but about saving them. We technologists need to do the same. Rewilding the internet connects and grows what people are doing across regulation, standards-setting and new ways of organizing and building infrastructure, to tell a shared story of where we want to go. It’s a shared vision with many strategies. The instruments we need to shift away from extractive technological monocultures are at hand or ready to be built.”
Since I am talking about what I like about AI, it’s good to share that I really appreciate Garbage Day’s regular dives into all the ways that AI content is terrible and weird and destroying what’s left of social media platforms. This from The AI Flight Attendants of Facebook is illustrative. Garbage Day is absolutely worth paying for.
“I assume these pages are simply jamming a bunch of popular stuff together to farm engagement to eventually monetize in some way down the line. Why AI images? Because you can flood Facebook with thousands of posts and the platform won’t really do anything about it. These pages are also using the platform’s built-in 3D photo filter, possibly to bypass Facebook’s bar-is-in-hell bare-minimum AI image detection. Why flight attendants? Because Facebook users are, and always have been, uncontrollably horny. But, also, my mom is a flight attendant (sorry mom if you’re reading this!) and aviation and flight attendant Facebook has always been huge. So I think they’re just identifying communities that were already active and swarming them. Why Jesus? Because religious content — and getting users to say “Amen” underneath it — became one of the fastest growing types of content on the site after it stopped promoting news content last year. “
“Birding has tripled the time I spend outdoors. It has pushed me to explore Oakland in ways I never would have: Amazing hot spots lurk within industrial areas, sewage treatment plants and random residential parks. It has proved more meditative than meditation. While birding, I seem impervious to heat, cold, hunger and thirst. My senses focus resolutely on the present, and the usual hubbub in my head becomes quiet. When I spot a species for the first time — a lifer — I course with adrenaline, while being utterly serene. “
“In culture and the arts, labeling something you don’t like (or don’t understand) “pretentious” is the easy way out. It’s a conversation killer, implying that any dialogue is pointless, and those who disagree are merely duped by what you’ve cleverly discerned as a charade. It’s akin to cynically revealing that a magic show is all smoke and mirrors—as if creative vision doesn’t necessitate a leap of faith. In this episode, Phil and JF explore the nuances of pretentiousness, distinguishing between its fruitful and hollow forms. They argue that the real gamble, and inherent value, of daring to pretend lies in recognizing that imagination is an active contributor to, rather than a detractor from, reality.”
