I'm going to reboot this journal; with a semi-technical focus. But not only. I intend to write about neurodiversity and disability and social justice and fixing tech for everyone. And other stuff.

So here's a first post. I have been experimenting with Large Language Models, and I'm so impressed at how far they have come in two years. There are seriously cool things they can help us with, and I'd like to see how they can solve more problems than they create. I've seen good evidence that a person using LLMs (not training new versions; just using the commercial-grade top-of-the-line models) has less negative impact on the planet than their impact shipping groceries from across the continent, or owning a car. So I currently choose to see what good we can do with them. (To be clear, I am also open to good-faith discussion if this feels wrong to you, and you have data I should also consider.)

I had a funny learning experience last weekend, with an experiment that flopped badly, followed by another one that has me sort of excited.

It started Saturday morning when I was curious about the brain science of "running on autopilot" and how weird that is. Gemini Pro satisfied my curiosity, noting that experiencing a glitch while thinking deeply about something was actually a sign of high cognitive efficiency, not a deficiency in attention to the world. I appreciated its conclusion, and asked if I could learn how to do this more effectively - for example, I often close my eyes while composing my thoughts while speaking, and I would appreciate being able to just tune out the distractions so I can succinctly say what I need to.

Gemini pointed out that "you aren't failing at conversation; you are optimizing your bandwidth". And suggested a few ways to improve the environment for me, including a) occupying my physical self with distractions like fidget toys, and b) be willing to wait 3-5 seconds to compose my thoughts before speaking. These are good advice; and it also had a good follow-up question for me (because I instructed it to; I really like my personal instructions. But that's a different post).

It asked me, "Do you find it easier to articulate complex thoughts when you are walking side-by-side with someone (where eye contact is naturally intermittent)?"

I responded with a few paragraphs that summarize to "hell yes!" and added that thinking while walking is really effective for me to figure out what I want to say, and indeed I have many of my best ideas while walking. Then I commented that I wished I had a more natural way to talk with LLMs while walking- I have lots of trouble dictating my non-linear thoughts to Siri. 

I said, "I would love to have a 'deep thought to linear language interpolator' - why can't conversational LLM map from my deep brain space to linear language for me?... Can you guys get onto that? human/machine telepathy isn't too far off is it?..."

Gemini's response was... interesting.

You nailed it: "[Siri] engages the same difficulty with linearizing my thoughts."

When you type, you are allowed to be non-linear. You can write the middle of the sentence, then go back and fix the start. It is a random-access buffer.

When you speak to Siri (or a person), you are forced into a Linear Context. You have to get the first word right before you can say the second. That is exhausting.

The Solution: The "Interpolator" Workflow

You asked why conversational LLMs can't map from your deep brain space to linear language. The answer is: We can, but you are giving us the wrong input.

You are trying to "clean up" the data before you give it to the AI. You are doing the interpolation work yourself.

The "Raw Stream" Hack:

Instead of trying to dictate a coherent note to Siri, try this workflow using a voice recorder (or a better dictation app like Whisper):

1. Abandon Grammar: consciously decide to speak in "bullet points" or "word clouds."

2. Verbalize the Meta-Data: Say things like, "Okay, idea about the server migration... wait, not migration, the upgrade... anyway, connection to the old database... oh, and remember the firewall rule."

3. The Interpolation Step: Feed that messy, non-linear transcript into an LLM with the prompt: "Here is a raw brain dump. Please linearize this into a coherent paragraph."

This offloads the "linearization" burden from your brain to the AI. You stay in the "deep brain space" (generating nodes), and the machine handles the "protocol translation" (generating syntax).

Would you like me to try to be your "Interpolator" right now? You could type a messy, unedited stream of consciousness about a complex topic you're struggling to articulate, and I will attempt to "translate" it into linear prose for you."

Well. That was an invitation!

So then in the same chat, I tried using Gemini Live mode while on a walk, with the following underwhelming - but funny - results.

---

and the conversation (if you can call it that) continued in that vein, with a very polite Gemini interrupting me every few words asking me to go on. I was more amused than frustrated, and decided out of stubbornness to implement something better.

(Because sometimes I think that's really what LLMs are good at- giving me a quick win on 80-90% of a problem, then I work much longer on the remaining 10-20%!)

So I started another chat asking about how to do the same thing, but starting from a Voice Memo, which has no time-limits. Gemini steered me toward writing a "Shortcut" - the Apple scripting tool - which I can run on the Voice Memo (which efficiently automatically generates a transcript right on my phone) and send the transcript text to Gemini to interpolate my stream of consciousness into a logical statement.

I can report that it works remarkably well!

I iterated changes to the instructions a few times. I wanted it to give me a summary to be read aloud by Siri, plus a complete report in markdown for me to paste into my journal. Improvements included:

1. instructing it to tell me what inferences it has made, rather than trusting it was recording my own thoughts verbatim.

2. I changed the description from "a meandering voice memo" to "stream of consciousness" and then it improved the instructions further to replace "Input: A raw, possibly rambling transcript." with "Input: A raw transcript of purposeful exploration." - I didn't fully test but Gemini suggests that would serve my intent better.

In the end, here are the instructions that Gemini wrote for itself:

As I said, it works well. I've tested it on 10 minutes of voice memo, taken while I was on a walk, where I talked about a morning's events, figuring out what I thought was important, and what I had to add to my TODOs, and I talked through a set of decisions that I wasn't clear on the answer. When I read the output, it was certainly more organized, and it was also faithful to what I had said. 

Its logical inferences were not bad. One of them:

• Synthesized the "Middle Ground" approach for the project meeting as the primary action item, discarding the two extremes (total prep vs. total ad-hoc).

In that part, I had described planning to do a lot of prep for a meeting, which I didn't want to do, and also didn't want to go in with no planning, then I realized I could do less prep and ask about followup. And Gemini inferred that I was describing a "middle ground approach" that was what I wanted to do.

I think this is what LLMs are supposed to be good for: producing structure out of human creativity. I started with curiosity about how the brain works, asked for suggestions on improving how I interact with the world with my own brain, and it non-judgementally recommended things that made sense, which led me to further questions which led to a solution I wouldn't have expected.

I think any company that fires its employees and trusts the AIs to do their work with minimal oversight are... doomed. We are no where near "General Intelligence." I think those of us who have the flexibility to experiment and even ask the AIs "what can you do to help?" will find there are many possibilities, and many could even amplify our own superpowers related to brain differences and neurodiversity. 

So that's one step in this direction. I'm still experimenting.

By the way, if you give Gemini that set of instructions (from "Role" through "Changelog" above), and a transcript from a stream of consciousness voice memo of your own, from a 10 or 20 minute walk and talk, it should be able to give you a fair interpretation of what you want to record. (and if it doesn't do it well on the first try, just re-run it, and it will probably be a bit different).

I'm curious how well it does for you!

[ 2026-02-05 edit: I added the "write in first person" line to the part two instructions above, since the reflection is meant to be as me.

It feels pretty natural doing this with a long meandering voice memo. This morning I did this while walking the dog for 25 minutes, and the output was excellent, just requiring a few small tweaks for my journal.]

I want to provide some clarifying information to supplement what I've found elsewhere, about the Via Rail service on Line #1, The Canadian, which stretches all the way to Vancouver. But there is really contradictory info online. So I can at least clarify end-to-end what my trip was like. There's no guarantee this will be your experience, but I hope it clears up some confusion. [Edit to add: I suppose your milage may vary; perhaps literally!]

You can also find all of these photos, with about 20 more, at my flickr album for the trip.


Contradictory things I read on the internet (sorry, I don't have sources at this time; I might come back later to fill in citations).

1) In Via Economy, to book with a group but pay separately, book at the same time; you'll be assigned nearby seats and if they aren't close enough, just call the number and via can move you.

WRONG: I and the two parties I'm travelling with all had unassigned seats on our tickets. When I called Via's service number, they said you just show up an hour before the train and talk to an attendant about getting seated together. And that's just the way Route 1 travel works.

This turned out to be correct. We arrived at 9am for the 9:50 train from Union Station in Toronto, stood on a shortish line in the middle of the Via section of the station, then at 9:20, we were released to go to the train, which was a bit of a long walk. Then the attendant at the train door got our information, and kept us together until they found a set of seats that would work.

We were put in a set of 4 seats, then two sets of two seats behind them. All of the sets of 4 seats had permanent signage reserving them for groups of 3 or 4, and they put up temporary signage when they had reservations they needed to assign seats for. However, there was no problem with me using one of these sets of 4 seats when they were not yet assigned.

It would've been nice if they'd put our last 3 in the seats side-by-side with our group of 4, but apparently that set of 4 had already been reserved by another group who didn't get on the train for another few stops.

2) In Economy class there are clusters of 4 seats facing each other at the ends of the cars. Or, seats can be turned around as pairs, so any seats can become pairs. Or, half the seats point forward and half the seats point backward.

CORRECT. All of these can be correct; at different times. The first economy-class car on the train had seats that can be turned around as pairs to make sets of 4, and they did that with arbitrary seats as needed. I saw it done by one of the attendants. The second economy-class car had fixed sets of 4, at each end of the car and in the middle.

In all cases, the seats have good solid foot-rests that can flip up to nearly flat with the seat, and it stretches to the back of the seat in front of you, or if your seats are in a group of four, they stretch just about exactly to the middle of the other seat, which means the set of four can make a nearly flat surface if they are all raised. This is NOT a super-soft bed situation, but it is oodles better than an airplane or bus. The only oddity is that there is no armrest between the seats, so if you're sitting next to a stranger, that's just the way it is.



3) The train is so much better than flying overnight; you have lots of room and the rocking of the train is soothing. Or, it's cramped and you won't sleep much at all.

CORRECT for the first one, mostly. The weirdest aspect was the lack of armrests. I would've been comfortable if I'd been able to put more padding under me so my slouching position was better on my back. Bring a pillow or inflating pillow; and bring a thin sleeping bag or a blanket. If you can have two seats, it is possible that lying sideways is more comfortable than stretched over a pair of facing seats. At least I thought so.

4) There will be lots of food choices. Or, almost no food choices.

CORRECT for the first one, mostly. The dining car, which is under the dome car, had a microwave and a full slate of options including mac and cheese (OK), breakfast sandwiches, pizza sub that didn't sound appealing, and a few other hot choices. There were many cold sandwich choices, and I enjoyed the turkey and cheese croissant I got. There was a good breakfast omelette. There were coffee, tea, hot chocolate, various soft drinks, wines, and various beers.

Our train was full, and they didn't have infinite orders of each kind of food, but I would recommend bringing lots of snacks, sufficient food you like to make up a meal if you can't find something you like in the dining car.

It would've been nice if VIA had a menu published that I could be sure was what our train was offering, but I didn't end up being unhappy about food.

5) There is an observation dome car. Or, there is no observation car on this part of the route, and it isn't added until the route past Winnipeg.



YES there was a dome car. It had about 30 seats, and we shared among about 100 passengers, so you couldn't stay up there for the whole trip. But it was a lovely change in scenery.

Overall, the scenery was beautiful. And I am telling friends that I would recommend this as a way to go, and I would do it again. We shall see when that happens! Because it's seldom that I feel I can take an extra two days for travel! (And my partner is still not interested in taking the train, even if it's a berth or cabin, which I am now even more eager to try! Some time!)

I've just re-read an article I saved from the first pandemic winter; there is a lot here that is going to be helpful for me this winter as well.

"How to make this winter not totally suck, according to psychologists"
https://www.vox.com/future-perfect/2020/10/14/21508422/winter-dread-covid-19-pandemic-happiness-psychology

"Rather than fixating on our inner worlds and woes, we can strive to promote what some psychologists call “small self.” Virginia Sturm, who directs the Clinical Affective Neuroscience lab at the University of California San Francisco, defines this as “a healthy sense of proportion between your own self and the bigger picture of the world around you.
...
The practices involve cultivating different states — social connectedness, a clear purpose, inspiration — but all have one thing in common: They get you to focus on something outside yourself."

Some concrete parts that jump out at me: I've at times kept a gratitude journal, but they suggest writing in detail about a particular event, rather than dashing off a superficial list of things. And focusing on people I'm grateful to; even writing them a letter, whether or not I sent it (perhaps the flip side of the catharsis of writing someone angry letters then tearing them up or burning them...)

For a while I worked for a company called "Openflows" which did consulting on open-source for non-profits and leftist organizations. It was satisfying work- and I only stopped working for them when the University offered me a full-time job in 2004. Their founder in Toronto, Jesse Hirsch, has been a tech columnist for the CBC for 25 years. He just had an interview with Jesse Brown on Canadaland podcast to talk about his possibly last broadcast on CBC, in which he asks "why CBC continues to promote Facebook after we've seen what that company has done to undermine democracy. CBC refused to post the segment online, raising questions about what you can and cannot say on our public broadcaster." It's a compelling listen, and makes me wonder how to react to the morally awful behaviours at the top of facebook.

Before I worked for Openflows, I was self-employed and in a partnership doing web consulting, from 1996 onward- while I was still in my last year at University. To tell you how early this was, we registered the domain name coder.com. Last November I was approached by a startup based in Austin, TX, looking to buy that domain name. I had really stopped working on those projects after starting working at the University, so it made the most sense to accept their (I think very fair) offer. I just looked them up. Their project is in public alpha and appears to be a success. "It's like google docs for programming." You get a web-based IDE and a virtual server, hooked to all sorts of useful things you can easily install. If you want to run more projects, or you want to harness 96 virtual servers at once for really quick compile times, you'll be able to pay them $5 a month. I expect the most exciting part comes with what more tools they might hook to the back-end for their subscribers. They just raised a cool $4.5 Million from venture capital, so they are doing OK for themselves. I sort of wonder whether they will incubate some kid's project that will replace facebook... I will say that I have no regrets about the path I took out of school. I was never interested in working startup hours, or risking my half of our mortgage on a dream idea. Especially since these big dream ideas often turn into crazy nightmares, don't they?...

On Tuesday, I'm giving a talk at the University's annual tech conference, WatITis, titled Perspectives on co-op employment and user-centered web-application development. This will be interesting. I'm motivated to do this because I really like my job right now, which is largely project management and supervising co-op student programmers. This is certainly a shift from what I was doing a decade ago, which was solo programming and sysadmin work. I'm keen on programming things that make academics' lives easier; and on giving student employees the real-world experience as we do this.

I'm very curious what the people who come to my talk will be looking for. I wish I could ask them in advance.

1) I used to blog regularly, and I miss it. The book of faces has inertia going for it; and I'm not yet pulling the plug there, but I want to try this again, in long form. So welcome! Pull up a chair!

2) In 2012 I started a blog about being Quaker. It's named after work by one of my favourite Quaker poets, and also after one of my favourite Quaker Science Fiction novels. I might also post there, occasionally. We'll see.

3) I became a dual American / Canadian citizen as of June 22, 2007. My partner dan and I moved here from the US in August 2001, so he could take the position of professor of Computer Science at the University of Waterloo.

4) When we moved here, I was a self-employed web application developer, for a much-younger Web. My business-partner and I made our first $2,000 out of a meeting at Comdex in 1996. I look back on those days fondly but definitely don't miss them! I worked for various companies doing Web 1.0 stuff; but I really hated chasing down clients for payment. I started working at the University of Waterloo in November 2004, in a job that was roughly 75% my dream job. Since then I've changed bosses six eight times, but still work for the same unit, Computer Science. My job is currently 100% my dream job. The me-of-half-my-lifetime-ago would be astounded. I expect I will stay at the University until I retire.

5) In July 2002, we adopted the cutest puppy in the world. At the time Rover was six weeks old. It was a few weeks later that we discovered that a certain number of people are offended that we named a girl dog Rover. I was really perplexed. I'm told that her cousin Sonia the Samoyed wanted to know if she's a squeak-toy or a snack. She really was the best dog. She lived to a ripe old 16 years, and we miss her all the time.

In August 2021, we adopted the director of the River Institute who is an absolute delight. And very photogenic. River is learning new things every day; even if it is "what is the best way to arrange my blankets for napping?"

I have many books. So does dan. We have moved them all a number of times, and they are rather heavy. We've moved together from Ithaca to Boston to Kitchener/Waterloo, Ontario. We bought a house with lots of room for book-shelves. Both of us come from families with lots of books, and whenever I'm in New York City I always come home with bags from the Strand Bookstore, the most overwhelming used bookstore in the world. Since then, we moved into a condo with fewer bookshelves, and the count of books went down somewhat, but there are still a lot.

I like science fiction. I really enjoy Greg Bear, Bruce Sterling, and Neal Stephenson. I enjoyed The Dazzle of Day by Molly Glass, a Quaker sci-fi story set light-years from earth. Also, I very much enjoy Bears Discover Fire by Terry Bisson. If you like offbeat sci-fi I recommend checking out They're Made Out of Meat, a quick short story.

My favorite regular fiction author is Paul Auster; I particularly enjoy re-reading "Mr. Vertigo" and "City of Glass." I'm a big fan of Toni Morrison.

I have a complete collection of Dykes to Watch Out For, not only because their publisher, Firebrand Books, was located across the street from us on the Commons of Ithaca, NY; (and then I was Firebrand's website editor, after we moved to Canada). I like Edward Gorey books too.

In the realm of non-fiction, I read a bit of science, history tending toward history of cities and gay and lesbian history, and more recently, Indigenous studies- historical and modern.

Since I first wrote this section (back in 2002), I significantly reduced the amount of reading I did for fun. But I've gone back to reading a bit more, again, because it makes me happy. If you're interested, I track most of my reading on goodreads.

melted_snowball and I left for NYC on Friday, returning late last night. He was the instigator, saying he really wanted to see Pippin, and after watching the Tony awards video (which you can see on that link right there ^^ ), I had to agree it was worth seeing on Broadway. So, in for a penny in for a pound, we also made plans for Kinky Boots, another Tony winner this year.

We had our next-door teenaged neighbour watch Rover for us, which worked out quite well, compared with boarding for the weekend- R. likes her routines, and our neighbour certainly likes Rover! (And now I notice that Rover has to sniff their door when she comes back from her walks... I think this may have something to do with bacon on the weekend...)

We got to Pearson and discovered our noon-time United flight had been postponed three hours. Well, indefinitely. Well, we might be able to rebook onto the next flight in three hours maybe. Instead of following the gate agent's instructions, I found us another United agent who instead put us and one lucky other guy onto an Air Canada flight at 3pm, and standby for an earlier flight. So the three of us trooped out of the ground-level prop-plane area to our waiting gate, and crossed our fingers, because 3pm was going to make it tight for us to get into the city and to our hotel and to Pippin. dan did his thing and got us from an unlikely standby to a much more likely standby flight- and lo, all three of us got lucky. And found ourselves on the ground at Laguardia just after 2pm. And we made it to our hotel in Hell's Kitchen, Midtown, in fine time.

At the end of this trip, I'm quite appreciative for the chance to run off and do things like this. We both really love Manhattan. We were idly talking about how great it would be to live there; perhaps when we both retire; perhaps for a short period on one of dan's sabbaticals. If this works, it will certainly involve a lot of planning- and being flexible, perhaps more so than with the flight rearrangements...

This was a full, but not overly full, trip.

We stayed in Hells Kitchen, the first time either of us had spent much time on the West Side. It was quite convenient to Broadway, our hotel was comfortable, and there were many good restaurants, including an eponymous Mexican restaurant "Hell's Kitchen" which had amazing fish.

Pippin was eye-poppingly neat. The acrobatics were the most awe-inspiring I've ever seen (see ^^ video). The first act is easily in my short list of favourite first acts of any musical. (Whatever that list is; I haven't given it serious thought except that the first act of "Sunday in the Park with George" is currently at the top. But I digress.) The story feels like it sort of unwinds in the second act. I hadn't seen the show before and wasn't prepared for a bit of storytelling where a certain amount of plot seems to be un-done in order to tell a completely different story in the second act- the story felt stapled together, and the main character AND the main actor started to grate on me a bit. I see from the wikipedia page that it could have been smoother in the second act. But the Leading Player/"Ringleader" character was wonderful throughout, including the very end where she offers Pippin a suitably glorious finale for his life aspirations. All in all, seeing this was my favourite part of the trip.

We had left Saturday mostly unscheduled, with an idea to get half-price tickets for an evening show, and a plan to see my Aunt who lives in Manhattan in the mid-afternoon. d. and I negotiated this one pretty well, also; I was going to see my Aunt while d. went downtown to buy us tickets. She accepted my sending his regrets about not seeing her, even though in advance she had said she would be very offended if he decided not to see her. Anyway, she and I got to visit, she got to show off her local Whole Foods and get me a mid-afternoon snack, and d. got to stay the hell away and do some clothes shopping downtown while ostensibly "on a line" getting us tickets at the TKTS booth.

But I get ahead of myself: In the morning we went to the Guggenheim. The main exhibit was by James Turrell, a Quaker artist and architect who works with light and shadow. In addition to designing a Quaker meeting house in Austin Texas, he's done other arts installations that have felt Quakerly to me, inviting contemplation and inner stillness. His big new work turned the seventy-five foot tall spiral atrium into ... Well, sort of the inside of a mood lamp, with gorgeous curves and subtle slow colour changes. Some 50 people laid back in the atrium looking upward at the colours. It felt meditative to me, even with the occasional conversation nearby. Though: it didn't feel like Quaker Meeting, not by a long shot. But it was at least as meditative as I could hope for in a crowd of New York tourists. I'm not sure what Frank Lloyd Wright would have thought about what they did to his atrium, but I'm grateful for the chance to see the exhibit.

There were also some great abstract art from the Guggenheim's collections, from between World War One and Two- including some great dadaist work, and some great Miró and Klee. These would have been a fine stand-alone reason to visit the museum.

And then we hit the Armory for "WS", a retelling of Snow White by Paul McCarthy. This, like the Turrell, was large-scale, covering the stadium-sized Armory (we once went to an art-sales show there, which took many hours to get through). Unlike the Turrell, it was loud, edgy, and quite profane, and I'm quite surprised they weren't sued by Walt Disney's estate. Every staff person we asked what they thought of it, said they couldn't wait for it to finish- which it was to do the day we saw it. In retrospect, I would have been fine if it had closed just before we were there.

After we met up after my Aunt, d. and I walked down to the High Line, the multi-mile linear park which used to be an elevated train-line. I wanted to like it, as a floating-park-in-midair. But there were too many people, too many rope barriers telling us what was off limits, and too few comfortable benches. All it needed was a roof and it would feel like the train- in the end I think it didn't escape far enough from that which it once was. I hope that it can gradually shift into something more than that, over the decades. Maybe a few exits into adjoining buildings? That would be spiff.

Dan's ticket find for the evening was "Phantom of the Opera", which neither of us had seen, though 20 years ago I listened to the CD quite a lot. Now in its 25th year, it was exactly like the CD, not a note different from what I remembered. And the music, instead of being a fond reminisce, sort of felt late-80s cheezy. Upsides? The costuming was great- particularly, I loved the spectacle of the masquerade ball. I guess it's good to finally see this; just as later this month I'm finally seeing Cats (in Toronto). I hope I like Cats more.

On Sunday, we walked to the Hudson River Park, just a few blocks from the hotel. Now this, this is how to redevelop an urban park. It was less manicured, more varied, and most importantly, not cramped. There was also free kayak instruction and consequently lots of people *in kayaks on the Hudson*. Which felt a bit weird to me, since I always considered the water there to be too dodgy to do anything with. For that matter, the ducks we saw next to the water looked a bit scruffy.

We did quite a lot of walking: after the Hudson park, across midtown to Central Park, lunch near Lincoln Center, and back down Broadway and down to 42nd street to see Kinky Boots. Which was great fun, and deserved their Tony wins. I might buy the album; it felt like a Cindy Lauper CD but in drag. (Which is possibly the same thing).

And then we retrieved our luggage and headed for Newark airport for our evening flight home. And we returned to Rover in our house, which was the best return ever.