I asked ChatGPT and Gemini how to make French Toast as good as my mother used to make — one nailed the crispy-sweet finish

AI French Toast
(Image credit: Lance Ulanoff / Future)

If you know me, you know my favorite food: French Toast. wherever I go, I order it, and I semi-regularly fire up my griddle to fry up my own custard-filled slices. Recently, I admitted to my wife that if I could eat French Toast every day, I'd do it.

My French Toast obsession is, in a way, an effort to recreate a core part of my childhood when my mother would make her ridiculously sweet and wonderful cinnamon French toast. I'd eat the slices as fast as she could cook them, only stopping when my mother decided I'd had enough. Decades later, I realize that I've still never had French Toast just like it. My mother's recipe, though unsurprisingly steeped in sugar, cinnamon, and butter, still seemed unique.

Latest Videos From

AI chefs show me the way

The two sets of instructions that came back are quite similar, and I was impressed by how both understood my desire to create something special and possibly crispy without burning the all-important sugar. You can see the initial results below.

I'm not gonna lie, ChatGPT did a better job of whetting my appetite by including a selection of delicious-looking French Toast image samples (two came from The Food Charlatan).

On the other hand, Gemini's no-nonsense approach got right down to the business of which bread to use (and why) and then the recipe for the custard (egg, milk, and vanilla mix).

Gemini also properly noted that I was looking for the "Brulee" approach and offered pretty straightforward steps, including drying the bread out in a low-temp oven before cooking, and a drop of neutral oil to lower the chances of the butter smoking.

Gemini French Toast 2

(Image credit: Future)

Gemini recommended I sprinkle some sugar on after browning the toast, and then watch carefully for it to melt properly.

ChatGPT's method was somewhat different. First of all, it actually told me how much sugar to use and had me premix it with the cinnamon on a flat plate.

It also — and here's where my interest grew — had me brown each slice, briefly remove and dip each side in the sugar mix, and then return them to the griddle.

This method immediately appealed to me because I knew I wouldn't want to be spreading sugar all over the griddle. Instead, I had full control.

Interestingly, both Gemini and ChatGPT methods recommended one to two minutes on each sugared side to achieve the crispy glaze.

I found that, one, I didn't have enough butter on the griddle, and two, 2 minutes wasn't enough to melt the sugar. I could've raised the temp, but then I risked burning the sugar.

In the end, I used the ChatGPT recipe (except for the bread-drying method and that drop of avocado oil), though I doubled the eggs, milk, and vanilla because I had twice as many bread slices. While I had mostly brioche bread, I did supplement with a few pieces of plain bread. I recalled ChatGPT telling me, "Yes, brioche is great—but standard sandwich bread works very well here."

Turns out, ChatGPT was right. In fact, those slides came closest to recreating my mom's French Toast. Each slice was sweet, crunchy, and sort of magical.

I'm sure Gemini's recipe would've been good, too, but I did not want to deal with that sugar mess, and sprinkling sugar would've resulted in an uneven crisp coat. Whereas the dip into the sugar plate put me in control. Also, I'm surprised that despite Google's wealth of online imagery, it did not try to entice me with any delectable images of French Toast.

Overall, it's just another example of why people are increasingly turning to AI for guidance on core life tasks. Platforms like Gemini and ChatGPT are so good at not just understanding the basic question but also the context and intention behind it.

I think my mother would be proud.


Google logo on a black background next to text reading 'Click to follow TechRadar'

Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.


TOPICS
Lance Ulanoff
Editor At Large

A 38-year industry veteran and award-winning journalist, Lance has covered technology since PCs were the size of suitcases and “on line” meant “waiting.” He’s a former Lifewire Editor-in-Chief, Mashable Editor-in-Chief, and, before that, Editor in Chief of PCMag.com and Senior Vice President of Content for Ziff Davis, Inc. He also wrote a popular, weekly tech column for Medium called The Upgrade.


Lance Ulanoff makes frequent appearances on national, international, and local news programs including Live with Kelly and Mark, the Today Show, Good Morning America, CNBC, CNN, and the BBC. 

You must confirm your public display name before commenting

Please logout and then login again, you will then be prompted to enter your display name.