AI Recipes

Artificial Intelligence (AI) is everywhere. It has slipped into our DMs on Facebook Messenger, appeared as an uninvited guest in our phones' list of apps, and infiltrated the social media platforms that once enabled us to connect with people we know and care about. AI is helping us to drive more safely, with enhanced crash detection and lane-keeping assistance. And it's annoying us on every website we visit, popping up as the helpful AI chat bot that no one requested. In all realms and sectors, it's omnipresent.

In education, everyone is grappling with this disruptive technology. It is changing everything we thought we knew about how to effectively teach students, how people learn, what skills are and will be valued in the workplace, and how to assess competency. There are some who want to ban it. Others are attempting to proactively engage with it. It's a hot topic for debate at many tables. Recently, in an effort to learn more about this pervasive technology and keep up with the pace of innovation, my colleagues and I have begun exploring the power of various tools, like ChatGPT and Copilot, to determine when and how they might be used in an ethical fashion to work smarter, not harder. 

We've had mixed results. Partly, the quality of the results depends on the quality of the prompt, so there's some learning to be done by users in that regard. AI appears to be incredibly effective at revising draft text or summarizing an extensive body of data. It also has some epic failures -- even when the prompt is highly specific. Now, admittedly, in my free time, a lot of my experiments have been revolved around making cute pictures of cartoon bears drinking coffee using Copilot. But as it executes a seemingly simple task (compared to mastering scientific literature, for example), I've been entertained to see the results and the limitations. For example, it produced a great image but misspelled the word "chocolate" as "choccolat." I asked it to fix the spelling while keeping everything else exactly the same -- and after five attempts, it still got it wrong (or fixed the spelling but changed the image). I had an abstract that was 2 words over the limit and asked it to shorten it. It told me it had done so, but then output the exact text I'd given it with no changes. Not so intelligent, now, eh?

During one of our coworking sessions recently, we started talking about how much we missed the energy bites that once appeared at every meeting. In these days of fiscal prudence, the stockpile we once had in the freezer has long since disappeared with no replenishment in sight. We wished we could get the recipe from food services, but figured there was no way they'd give it to us. I mentioned that I've looked at many recipes online, but haven't found one that is quite right. They all have been missing one or more of the ingredients we know are in them -- chia seeds, oats, chocolate chips, peanut butter, coconut. My brilliant coworker mused, "I wonder if Copilot could write us a recipe if we told it the ingredients." We temporarily put that in the metaphorical parking lot, finished the task at hand, and then rewarded ourselves with a quick Copilot prompt. In no time it produced a recipe.

Scanning the ingredients and the method, it looked like it would work. In fact, there was only one change that I would make: instead of mixing the dry ingredients first and adding the wet to them, I would mix the wet ingredients first and add the dry to them (only because peanut butter and honey can be a challenge to combine). We considered trying the recipe sometime in the future. For me, sometime was about 45 minutes later.

What can I say? I was curious. It was also a Wednesday -- and Wednesday nights are devoted to trying new things, especially in the culinary realm. To round things out, I had all of the ingredients on hand. It was meant to be.

I followed the recipe, making only one modification in procedure (mentioned above), and was impressed by what I saw. The mixture had a good consistency and the resulting bites looked a lot like the ones we had enjoyed at work in the past. The recipe was a success in the sense that it worked. But how would they taste? 

I'm happy to report that when we tried them the next day, they were delicious and a very close dupe. In my opinion, the amount of chia seeds could be reduced. My colleague observed that you can't normally taste honey when you eat the version made by food services. Upon reflection, given the cost of real honey (and maple syrup), we concluded that they probably use a cheaper sweetener, like corn syrup. We both thought that mini chocolate chips would be better. Regardless, they are "a keeper," as Trooper Ron would say. 

While this experiment worked, I'm not sure that I would necessarily recommend AI recipes to others. Presumably, Copilot and ChatGPT have trained largely on free online content (as well as books). The quality of recipes online, though, is variable (to say the least). Sure, some are delicious. But far more yield disappointing results -- in some cases, they are just okay, while others are total disasters that don't work. You're definitely taking your chances. 

But if you're trying to find an elusive recipe, it might be worth the gamble.  

White Chocolate Hearts

As I thought about what I should make for Valentine's Day this year, I realized that I had a large quantity of white chocolate left from my Christmas production run. Since several people in my circle love it, this seemed fortuitous. But it also presented a challenge. White chocolate is far more temperamental than milk or dark chocolate. It's easy to overheat it and difficult to work with. I decided it would be good practice and went to my stash to pick out a mold.

Originally, I was thinking about using one of the large heart lollipop molds that I have and making a solid piece. But that seemed pretty basic and I also didn't have any long lollipop sticks. As I shuffled through my options, I noticed a mold that I had forgotten existed. I'm not even sure where I got it, but it's clear from the fifty cent tag that I had picked it up at a bargain. Perhaps it came from the shop on Charlotte Street that closed several years ago. Perhaps I found it at a flea market. Whatever its origin, I knew I had only used it once to create treats for the CIBC Run for the Cure (I served as volunteer coordinator one year).

I pulled it out and examined it, trying to determine if it was deep enough to be filled with something. I figured it would work if I could keep the filling to about 1/4 inch thickness. I set about tempering the white chocolate and shelling the mold. Because it is flexible plastic instead of the polycarbonate molds professionals use, it was a little more challenging to shell properly. Nevertheless, about 15 minutes after shelling it, I confirmed the temper of the chocolate. Success!

Then I needed a centre. Inspired by the white chocolate Reese peanut butter cups and remembering how delicious the white chocolate peanut butter bark was that I made a few years ago for Easter, I settled on a peanut butter filling. I heated it up to be more liquid and discovered it was about two degrees too hot to pipe into the shells. I waited for the temperature to drop to a safer range and then piped the filling into the deepest part of the mold. I left it to set up, fully intending to cap them the following day. When the weather cancelled my evening plans, however, I reconsidered. I tempered another quantity of white chocolate, capped the hearts, and set them in the fridge to set for 15 minutes. Mercifully, when I took them out, I found that the caps were also in temper. 

After flipping the mold over and popping out the hearts, I was surprised by the colour of the chocolate. The shell was so thin that the peanut butter was visible through it, but it didn't crack and I couldn't see any sign of fat migration (yet). The contrast between the peanut butter filled heart and the solid white chocolate flames at the top lent some interest to an otherwise plain confection. I left them on a tray at room temperature for 24 hours to fully crystallize. 

Before the big love day, I wrapped each heart in red foil and placed a sticker on the back. (I also accidentally put my thumb through the delicate shell of one -- a perfect excuse to sample my work.) Voila! This year's Valentine's Day creation. Sure, it's not as complicated as last year's artistic dulce de leche espresso hearts. But these are a white chocolate and peanut butter lover's dream. Sometimes less really is more.

Happy belated Valentine's Day, y'all!

Lamingtons

I'm not sure why, but the idea of making lamingtons has been in the back of my mind for a few years. I can't really explain it. I believe I saw a YouTube video of someone making them during the days of isolation in 2020. And then, of course, once you watch one lamington video, the algorithm rips the rug out from under you and you plummet down the rabbit hole. While I didn't recall eating them before, they reminded me of other desserts involving coconut that I'd seen as a child. And they certainly seemed like the sort of dessert Newfoundlanders would appreciate -- a layer of jam inside, the outside coated in coconut. In the words of Ina Garten, how bad can that be? 

When I started looking into recipes, I stumbled upon one by Barry Parsons who shares Newfoundland recipes on his Rock Recipes site. According to him, these creations were popular in Newfoundland during the 1960s and called chocolate coconut cake squares. And they weren't limited to one flavour -- raspberry and strawberry variations were common. Indeed, its the pink cake coated in coconut that I member seeing when I was young. Parsons also provides a lemon variation that sounds delicious! Decision made! Lamingtons would be this year's "cake" for a friend's upcoming birthday brunch. 

I chose to make the Cupcake Jemma recipe because I believe that's where I first saw them being made, but opted to add the jam layer that I'd seen in other variations. I started this culinary adventure on a Wednesday night, when I made the cake. First I mixed the sugar, eggs, and vanilla. Then I folded in the flour and baking powder. Finally, I add the melted butter. I poured the thick batter into an 8x8 pan lined with parchment paper and popped it into the oven for 25 minutes. Once a toothpick came out clean, I transferred the cake to a cooling rack before wrapping it well and setting it in the fridge overnight. 

The adventure continued on Thursday evening. I torted the cake using a Wilton cake leveler and filled it with seedless raspberry jam, taking care not to add so much that the layers would slide around. Then I wrapped it well and popped it back in the fridge to chill.

On Friday, I made the chocolate icing. What's that you say? More butter? Did Julia Child write this recipe? Once the icing was glossy and fluid, I cut my cake into 9 pieces and trimmed off the caramelization. I dipped each one into the icing, followed by the coconut, and placed it on a cake rack while I coated the remaining pieces. I kept three pieces coconut-free for my boyfriend (and other coconut naysayers). Then I returned them one more time to the fridge to fully set. 

Initially, I admit, I was a little concerned about serving lamingtons as birthday cake. I was primarily worried that they would be too small and look more like the squares you see at a church social. But once dipped in chocolate and coated in coconut, they looked much more substantial. The result? A delicious buttery cake with a slightly tart jam layer in the centre, surrounded by super sweet icing balanced by a coating of unsweetened coconut. The cake was more dense than I'd anticipated (I'd been expecting more of a sponge cake), but that may be a result of the particular recipe I chose. 

As for the leftover chocolate icing, it made the perfect base for a decadent hot cocoa!

See you next week!

Rock Candy

February 5, 2025 Update

The rock candy experiment was successful! 

Look at this beauty!

- - - - - - - -ORIGINAL POST - - - - - - - -

Earlier this week as part of my candy course, I watched a video on how to make rock candy. Now, the method wasn't exactly new to me. I think most people are first introduced to this concept in grade school as a science experiment involving a supersaturated solution. But as I sat watching the demonstration, it occurred to me that despite knowing about this for the better part of my life, I'd never actually tried it myself. Clearly the time had come. Challenge accepted, Tony Morris!

The recipe called for more than three cups of sugar and I could see that the candy maker had syrup left in the pot after filling a jar, so I decided to cut the recipe in half as I was measuring out my ingredients. I probably made my life more difficult by doing that, but I also didn't want to create a lot of waste. I only had paper lollipop sticks on hand and imagined that would be unpleasant at best when eating the rock candy, so instead I used the blunt end of a bamboo BBQ skewer. I expected that I would only have enough syrup to produce one rock candy stick, but prepared a second just in case. Then I rigged up a few mason jars with post-it note "lids" to hold the syrup. Finally, I went into my handy tool kit -- a gift from my father when I first went off to university -- and pulled a clamp to suspend the skewer in the solution. Probably not what he was imagining when he gave it to me, but here we are. Armed with a thermometer, I prepared the solution.

Now, dissolving an obnoxious quantity of sugar into a very small amount of water is no easy task, but if you take your time, adding a little as you go, you eventually get it done. I was surprised by just how thick the syrup was. The sweet and sour bar mix I made a few months ago for a Halloween party couldn't hold a candle to this. I decided that green apple was the perfect colour-flavour combination and stirred the syrup to distribute the colour. Finally, I carefully poured the syrup into the jar, suspended the skewer in the syrup, and set it aside to do its thing for a few days. 

Within hours, I could see crystals forming, but it appeared that they were growing more rapidly than they should. On day three, I decided to open the jar and see what was happening. I certainly had crystallized sugar, but there would be no getting the candy stick out. What I had was a candy stalagmite. The texture would have made a great centre for a chocolate geode, but was definitely not what I was going for in this experiment.

As luck would have it, we then had a snow morning. And that meant take two for the rock candy. I thought I knew where things went wrong the first time, so I modified my technique a little and set up a clean jar ready to receive the sugar syrup. Immediately I could tell this batch had more promise. I left it  to cool without disturbing it. 

Twenty-four hours later, I could see a few crystals starting to form on the stick, much slower than the first batch. I took that as a good sign. 

Forty-eight hours later, the characteristic large square crystals were gathering on the stick. 

Seventy-two hours later, I posted this blog. I had hoped to have a final product by the time it went live, but sugar has a mind of its own and can't be rushed. 

When I finally do remove the rock candy from the mason jar, I'll update this post. I can't wait to try it!