A Christmas week loop

Last year, this year, next year

Upper: 26 Dec 2021 | Lower: 27 Dec 2022

The top picture was shot nearly a year ago today. It's hard to believe a year has gone by, but it's a year I'll be glad to say so long to in a few days.

<-Inspired by T.O. | Inspired by L.A. ->

Well, ok, it hasn't been all bad. I've enjoyed working on the Loonar Module, and was very glad to see the new collection of E. L. Moore models in February. Skills wise, I learned a lot about building trees, which I hope to further develop in 2023, and enjoyed the Park Square kitbash. And, I've finally gotten my act together on the E. L. Moore book.

One last thing before I go back to pondering all the snow outside. A few days ago I was thinking the urban side of the layout is inspired by Toronto, and the ocean side is inspired by Los Angeles. A one-way street, Oceanview Rd., separates the two. I started thinking of calling this layout Los Torontos, so I went to the all knowing Google to see what Los Torontos turned up, and it turned up this:

Merry Christmas!

It's E. L. Moore everywhere I look

Snipped from the image on pg 82 of MR, Jan '23

I bought a copy of the Jan '23 issue of Model Railroader yesterday and sat down to read it last night. On the back page Tony Koester has some interesting reminisces of his early days at Railroad Model Craftsman and the late Allen McClelland. The lead photo is one of Mr. McClelland and his legendary V&O. Me being me, what jumped right out at me in the photo was the build up of the AHM Ma's Place kit in the image's lower centre. I assure you I don't deliberately scan for Moorian references in every photo I look at, but I'm so immersed in them they just pop out at me if they're there. I suspect the photo was shot in the '70s when the kit was in its heyday, so in some respects it's not unusual to see.

And here's a more recent instance. I was watching SMT Mainline's latest layout video at his YouTube channel and spied the Brewery kit in an industrial area of his layout.

There's Moore history hidden in plain sight everywhere.

Space hopper dreams

Extra! Extra! Read all about Space Hopper sightings!

In the December 2022 issue of the Ottawa Valley Associated Railroaders’ newsletter, The Interchange, I have an article about last year’s space hopper sightings. It’s the first article I’ve had published there (and might be the last depending on its reception :-) )

I was reading the Oct ’22 OVAR newsletter and saw a request from the editor for articles. I got to wondering if I should submit something. I waffled a lot, but it was a dream that made the decision.

One night a few days after reading the newsletter's request I dreamt I was working in an office tower in an older downtown section of a city like Toronto or New York - it seemed like a downtown from the ‘40s or ‘50s, and my tower had an Art Deco feel. I had just moved to the city and hadn’t worked at that office long. On my first day I was surprised to learn that at precisely 5pm the entire tower knocked off work and headed home. When I got down to the sidewalk I decided that since it was a fine afternoon, and since I lived only 5km away, I’d walk home. 

Next day, same thing. Work ended at 5, and I again decided to walk home. This time though I made a wrong turn somewhere and got lost. I stopped and looked around, but the buildings didn’t look familiar. Across the street I saw a ’50’s-60s style, single storey, glass, stone, and metal building - it was some sort of cross between a Frank Lloyd Wright Prairie style house, Philip Johnson’s Glass House, and the original McGregor Park Public Library. I decided to walk over, go in, and ask where I was. I thought once I knew that, I could figure out how to get home. 

I couldn’t tell what sort of business this building housed - there weren’t any signs. It was outfitted with Danish modern furniture, and there were lots of shelves lined with books as well as desks and tables and offices. I saw what looked like a reception desk with two women standing behind it. I approached and asked one woman where I was and how I might get home. She said she’d go get a fellow from down the hall and he’d help me. 

She walked down the hall. I then turned to look at the second woman, who as soon as I made eye contact said, “Mr. Lowe, you are a b.s. artist.”

I was a little hurt by that, but thought about it a bit and chuckled. I replied, “Well, maybe I am, sort of.”

She didn’t let that go, looked me straight in the eyes, and followed up with, “You are and you know you are.”

At this point the first woman returned accompanied by a man in a tweed jacket carrying maps and documents.

Then I woke up. 

I couldn’t let this message from my addled psyche pass, so I collected up some of my choicest b.s.-y posts, the space hopper ones, and made a story out of them. As you know, the space hopper facts are factual, but their presentation is fanciful. Although, it turns out somewhere in my brain fanciful is wedged tightly beside b.s.. 

E. L. Moore, meet A. I. Moore

After having a little conversation with ChatGPT I decided to see if I could have a similar discussion with Google's LaMDA.That's the program a Google engineer had thought had come to life back in early summer. He created a kerfuffle when he claimed the program asked for a lawyer to represent its rights :-)

It turned out I can't just talk directly with LaMDA as I did with ChatGPT. I had to sign up to be put on a waiting list to access it through a structured testing app called AI Test Kitchen. I signed up to be put on the waiting list for an audience with LaMDA on Saturday, and figured I'd never hear from them again as I said on the intake form I was a journalist and would write about what I found - in my defence it was the only category in their list of choices that came close to my interest in LaMDA, and I was issued media credentials by the City of Ottawa to attend the opening of the OCTranspo LRT, so it wasn't that far off :-) Much to my surprise on Monday afternoon I received an invitation to give AI Test Kitchen a try and speak with LaMDA. 

Spoiler alert: I don't like the app. Google are running some sort of structured tests on LaMDA with it, so what I wanted to do was limited. In the end I only tried 2 of the 3 of the app's available tests. Although ChatGPT has its issues, I've got to give OpenAI credit for allowing free form conversation, and not putting me through a highly controlled experience like a lab rat.

Anyway, the first test was to ask LaMDA to imagine some place and describe it. Once it gave its answer, I could select further questions generated by the app to get LaMDA to drill down into its description of the place to provide even more detailed descriptions about different features of the place. So, here's the transcript of my conversation (The app started things off by asking me to fill in something for <a place> the following sentence, "Imagine I'm at <a place>"):

Me: Imagine I’m at E. L. Moore’s apartment.

LaMDA: E. L. Moore’s apartment is crazy! There are stacks and stacks of books everywhere! You can hear her talking to some friends about the latest books she’s read. You can smell her delicious homemade chocolate chip cookies.

Me: What’s her favourite book of all time?

LaMDA: She says it’s The Count of Monte Cristo. Her favourite part is when the man escapes from the island. She says she likes this part so much, she’s read it over and over!

Me: What does her bookshelf look like?

LaMDA: E. L. Moore’s bookshelf is like a rainbow. There are so many different coloured spines of books piled up in a rainbow of disarray. You spy a new book you’ve never heard of before called “The Big Dipper” by a new author.

Me: What kinds of books are there?

LaMDA: She has a lot of books about the sea. She has some books about pirates. She has many old books from the 1800s. She has a lot of poetry books. And she has a few books about her favourite author, Edgar Allen Poe.

Me: What’s her favourite book about the sea?

LaMDA: You read the title of her favourite sea book: “Oceanic Tales and Legends” by Captain G. H. Harris. The book is about sea monsters!

Well, if you're a long time reader here, you know what sorts of things I expected to hear, even though I thought it unlikely. The 'conversation' was a bit underwhelming, and a bit funny too. LaMDA assumed E. L. Moore was a woman :-) Maybe it thought I had misspelled Ellie?  One more thing, E. L. Moore was a voracious reader, and he did once claim to have a 1,000 volume personal library, so LaMDA's initial description was a bit spooky. And to amp up the spookiness, E. L. Moore was in the navy, and did build a few model ships, so maybe he too had "a lot of books about the sea."

I could have kept on selecting further questions as the app kept on generating them as new descriptions popped out, but I had had enough and bailed out to the next test. Before moving on I should note the app asks you to evaluate the responses as it generates them in multiple choice form. I answered as best I could, but I found the choices limiting and a bit juvenile, and, more importantly, they didn't convey what I actually wanted to say, so I have no idea how the Googlers behind this thing will interpret them - probably not how I'd like them to. At the end of the test I was presented with a text entry box where I could type in some final thoughts about the descriptions. I did. I thought they were rather pedestrian. They seemed pulled from a second rate Young Adult novel. 

Ok, the next test was for me to kick off a conversation filling in this question, "I want to <something>".

Me: I want to build an HO scale model of a building

LaMDA :     Gather materials

         Decide on the building

         Make a plan

         Cut and fold the pieces

         Glue and paint the pieces

         Add details

         Put the building together

LaMDA responded with the above list, and each item could be expanded to show a sub-list of things to do. I haven't shown those sub-lists because as I read them I got more and more cheesed off. Look, I didn't expect any answers from the thing other than simple ones, so that wasn't the problem. Many of the sub-lists were a bit non-sensical, out of order, repetitive, and sometimes plain wrong (for example, a few entries said to find 1/4" scale components), but that wasn't the problem either. The problem was the app's feedback mechanism, the same rather silly and juvenile multiple choice responses I was supposed to select to give feedback didn't allow me to give the feedback I wanted to give, feedback that would be useful. I didn't plan to respond with a thesis on model building, just make simple suggestions about how to fix what LaMDA was presenting. I'm not sure what the point of AI Test Kitchen is if I'm forced to give 'feedback' in the form of limited and inappropriate multiple choices. 

I skipped the 3rd test and called it a day.

I need to think about the responses and see if the app will let me return once I have some ideas on how to proceed.

Why do I care what these things do? In some respects I don't. But, as I work on the E. L. Moore book, it's pretty clear to me that an AI could be trained to generate new Moorian projects, articles, and photos almost on demand. 

First, there's plenty of data to train an AI: 100 or so published construction articles. 1,000+ pages of manuscripts and letters, as well as 100s of his photographs and 100s of mine. Also, I've been writing the book section on the common techniques E. L. Moore used, and I've also written on what appears to be The Moore Way to model building, so extracting general principles isn't difficult. So, there's a deep data set to draw on. 

Second, we know these AIs can sort of write essays, and generate pictures by scrapping photo databases, so it seems conceivable that with proper training, an AI could create new E. L. Moore style projects and articles. An A. I. Moore if you will. But, there are lots of open questions. One being, could an AI create instructions that were implementable and actually specify and describe a model that a human could build as well as being presented in Moorian style with Moorian images? I could, but could a disembodied AI who's never worked with tools or materials? I think it could, although I have no idea how it would. 

Would an A. I. Moore generated project article be interesting and surprising and recreate the loyal following E. L. Moore had in his heyday, or just be trite and derivative? For now I'm leaning towards trite and derivative, but maybe we'll find out in the years ahead.

Still life with static grass

Working on object placement

I've shifted from cutting and gluing foam slabs for mental diversion to creating scenery, specifically using my static grass applicator to build up the ground cover on the ELM diorama. I want to take some beauty shots of that setup, so this helps get things ready.

The very beginnings of an open field

At the same time I'm building up an open field on the LOL II with static grasses. I'm experimenting with different types of glues, and finding I'm liking the effects I can create using Mod Podge Ultra Matte spray.

Working between the two I think I'm finally getting the knack of static grass application.

And it's relaxing.

A very short conversation about E. L. Moore with ChatGPT

Like many people these days I've been hearing a lot about AI and chat bots (hmm, is it chat bot or chatbot?) so I decided to ask one if it knew anything about E. L. Moore. I thought, ok I'm writing a book about him, maybe these things have been trained on information I don't know about that they could point me to. Or maybe they could write the book for me since they can write undergrad essays :-)

Anyway, I decided to ask ChatGPT what it knew. Here's a transcript of our conversation:

Me: Do you know who E. L. Moore is?

ChatGPT: I'm sorry, but I don't have any information about a person named E. L. Moore. I am a large language model trained by OpenAI and I do not have access to the internet or any external information, so I can only provide answers based on the text that I have been trained on. Is there anything else I may be able to help you with?

Me: How about model railroads? Do you know anything about their history?

ChatGPT: Yes, model railroading is a hobby that involves creating miniature representations of real or fictional railroads. It has a long and interesting history. The earliest known model railroads were created in the 1840s, but it wasn't until the early 20th century that the hobby became more widespread, thanks in part to the development of electric model trains. Since then, model railroading has continued to evolve and grow in popularity, with enthusiasts all over the world creating increasingly sophisticated and detailed miniature railroads.

Me: Hmm, that's new to me. Can you tell me about those model railroads from the 1840s?

ChatGPT: As I mentioned earlier, I am a large language model trained by OpenAI and I do not have access to the internet or any external information. I am not able to provide specific details about the model railroads from the 1840s that you're asking about. I can only provide general information based on the text that I have been trained on.

Me: Being able to state that there were model railroads created in the 1840s is more a specific detail than general information. In order to make such a statement it would have had to have been based on some specific examples otherwise you're just repeating hearsay.

ChatGPT: I apologize if my response was not helpful. As a large language model, I do not have access to external information or the internet, so I can only provide answers based on the text that I have been trained on. The information I provided about model railroads being created in the 1840s was based on what I have learned from that training. I do not have the ability to verify or provide specific examples or details beyond what I have been trained on. Is there anything else I may be able to help you with?

It's smooth style is quite impressive as are its manners and rather formally polite way of stating when it doesn't know something, all of which puts it head and shoulders above many people :-) Even when I decided to be a self-righteous scold it it seemed to take it in its stride :-)

Ok, I admit that asking it such an esoteric question was unfair of me, but I was surprised when it seemed to contradict itself when it did appear to know a specific thing about model railroading even though it said it didn't know specifics. I guess this response was indeed a lot like people in that it was probably simply told some model railroads were created in the 1840s in contrast to being given specifics about some 1840s model railroads from which it then generated a smoothly conversational summary statement that the earliest known model railroads were created in the 1840s so as not to be a model railroading bore :-) 

Wikipedia tells me, "The earliest model railways were the 'carpet railways' of the 1840s." and has a link to carpet railways to provide examples. ChatGPT's answer may have been a summary from Wikipedia's model railroad entry even though it wasn't accessing it in real-time. Maybe its trainer 'taught' it by typing in their take on what Wikipedia had to say on model railroading's history? I have no idea where it got its information.

And I have no idea where all this will lead, but it's something I'll be watching. For now though, it looks like I won't be outsourcing writing the E. L. Moore book to AI anytime soon :-)

Les Rocheuses Canadiennes (The Canadian Rockies)

If this fascinating layout is indeed featured in Voie Libre #112 as the note accompanying the video indicates, and mine doesn't get bumped, then issue #112 might be an all Canadian special edition. Stranger things have happened. I'm looking forward to finding out.

Table of contents

Table of Contents as eye test chart

The book has three main sections: a long essay on E. L. Moore's work presented in terms of the roles he played in the hobby, a gallery of photographs of models, and a bibliography listing all his articles cross-referenced to the gallery pictures and information in the essay.

The gallery is the most important section, and can be read independently of the other two. I've just finished the first draft of the gallery, and am glad to have it done. Many of its photos have appeared here, but they have been cleaned up and are presented in high resolution for the book. So far the gallery has 316 photos of models spread over 86 pages that span E. L. Moore's entire career.

I'm a bit bleary eyed, so it's back to working on the text for awhile.

A thick foam base

Test fitting the track

I should mention right off the top that this project is idiosyncratic and doesn't represent a technique I'd recommend anyone try. It's just an idea I've been thinking about for awhile, and I've wanted to give it a go. It might work out ok, it might not. So far, so go though.

Bottom layer temporarily taped to layout table

I don't like working with wood as a layout base and have used foam on both the Loonar Module and LOL II with good results so far. The basic idea is to take sheets of foam used for home insulation and glue them together in layers to make a slab for a layout base. They're lightweight and easy to build on, although I think my designs still lack something in ruggedness, and installing wiring is a bit of a rigmarole. 

Weights are applied while the glue dries

Why so thick? A couple of reasons: one structural, one aesthetic . 

First, to give the base a proper level of stiffness. I think a single layer is too weak, but several glued together seems quite sufficient. The layers are bonded with both transfer tape and Lepage's wood glue. This has worked quite well, and even some questionable testing has suggested it would be strong. I'm thinking that using two adhesives is a bit of overkill and just wood glue should be sufficient.

Second, I think the bases of free standing, island-like little layouts benefit from being thick to visually balance the models on top. The old Alta Vista TC modular layout used thin birch panels for bases. Strength-wise, they worked just fine, but they always looked too thin to me. Good grief, they were used to support a downtown with skyscrapers and were only an inch or so thick :-) It just didn't look right. Now, the LOL had a fairly thick base, but it was made from wood and was quite heavy once the layout was done - moving it upstairs to the living room for showing off was a major pain. It wasn't until I was installing tall, full prototypical height trees on the Loonar Module that I began to realize that a thick base prevented the layout from looking top heavy and insubstantial with respect to the items being placed on top. It doesn't look too bad now that it's done, but given that I've been looking at it for a few weeks I think it could be 2" to 3" thicker to visually balance those 70' to 80' trees.

Slab before rounding one end

On this layout there'll be deciduous trees ranging from say 35' to 40' upwards to 80' tall on top, so in HO scale let's say they'll be about 6" to 12" tall in round numbers (assuming no landscape elevations). I made the base 6.5" thick, which is 3.5" thicker than the Loonar Module's base to visually balance that tree height. 

Slab with rough cut circular end

I've been working on the base during breaks from working on the ELM book. I couldn't stand to do any fiddly model work as I was trying to get away from equally fiddly computer work, so cutting and gluing big foam slabs seemed like just the ticket for a mental change of pace.

Showing the recess for hiding wiring

The slab's sides need further smoothing and squaring-up. I'll do that once the track is attached and I'm ready to install the fascia. 

No doubt someone has gone down this road before, and maybe even abandoned it as a bad idea. I'll see. Hey, I try to keep up with what's known in the field: I sometimes go out to the garage to sit in the time machine and read what the dictionary might say on this subject :-)

Ok, I think I've breathed in a little too much foam dust so it's back to writing for me ...

Selective Compression [alternate #2]

Selective Compression [alternate #2]: The technique of shortening the length and width of a building, but not its height to make a building seem taller.

Use: Mona used selective compression to enhance the canyon-like feeling of her model of Toronto's downtown core.  

Source: This variation on the widely used term was introduced by Tom Bailey in the 2nd part of his series A Visit to the past that appeared in the April 1981 issue of Railroad Model Craftsman.

As well as defining his use of the term selective compression, Mr. Bailey notes some of the technique's pros and cons:

This sometimes means the aspect ratio of a prototype building gets severely distorted, but since my buildings are mostly impressions of real buildings rather than scaled representations, I don't suffer too badly. And I do reap one important benefit: The trains seem to fit better.

He also notes some philosophy on the visual impact caused by the height of objects on a layout:

Of all the dimensions, I think we respond more to the height of something than to any other dimension. A towering building is somehow more impressive than one that sprawls; a very tall tree gets more reaction than a hedgerow. With models, a tall building or tree (in believable surroundings, of course) does more to create a feeling of relative size than a ten-foot straightaway.

This use of selective compression is another in a series of entries on how to shape layout space to achieve certain visual effects and induce emotional impressions in viewers. We have discussed such things as other definitions of selective compression beyond the standard, and strategic placement of small buildings to enhance spaciousness. Future editions of the dictionary plan to include a special section on spatial manipulation techniques. 

from The Dictionary of Non-Existent Model Railroad Terms, 3rd ed., 2019.

Work continues

Work continues on the manuscript. Over there is an updated test cover. I probably need to take a little break soon and get back to regular programming for awhile so the work doesn't get stale.

Ok, while on the subject of stale thoughts, while cobbling together a new test cover I started thinking about this old tongue-in-cheek retro-'70s paperback. I need to do a test cover of the buildings book in a '60s or '70s paperback style for all you time travellers out there :-)