Close Ad

The Spoon

Daily news and analysis about the food tech revolution

ChatBot

How ChatGPT Is Going to Make You a Better Cook

You’ve probably heard of ChatGPT by now, the AI-powered chatbot wowing technologists, journalists, and a whole bunch of Twitter users with its ability to understand human language and give realistic human-like responses.

The New York Times called ChatGPT the “best artificial intelligence chatbot ever released to the general public” while others have speculated how the technology could change industries ranging from banking to healthcare.

Since ChatGPT has been used for everything from sending clients emails to writing poetry, I figured I’d play around with it to see how it could help me make a better cook.

The first thing I thought I’d do is see if the chatbot could help create a recipe with some interesting flavors. I asked it to make a bread recipe “using beer, chocolate and Rice Krispies” and, after a few seconds, a recipe complete with cooking instructions appeared on my screen:

Sounds good to me. I mean, who wouldn’t want a beer and chocolate bread recipe featuring Rice Krispies?

When I asked Google the same question, no recipes that featured beer, chocolate, and Rice Krispies in the ingredient list showed up. In fact, every time I asked ChatGPT for a recipe suggestion, the results were as good or better than the results from Google.

But where ChatGPT really shined is its ability to remember my previous questions and build upon those for very context-specific responses. Take, for instance, my query for a pasta recipe that featured red sauce and garlic. ChatGPT’s initial response was a recipe that looked good, but it was a recipe that could have easily been found with a Google search.

When I asked for a Keto-friendly version of the pasta recipe, ChatGPT considered the specific recipe and gave a pretty good answer about how to fit the specific dietary profile I wanted:

As you can see, ChatGPT makes the process of figuring out a meal something closer to a conversation with a chef or a culinary planner rather than the traditional process of piecing together search engine queries. In fact, I found I could build an entire meal plan using the chatbot, including things like wine pairings…

To side dishes…

And it’s not just flavor pairing and meal planning where ChatGPT shines. Because the chatbot has a wide breadth of understanding of pretty much everything, you can ask it for advice about how to use food in a variety of different situations, such as life events:

Or when someone you know may need a little pick-me-up:

Not every response is perfect, and some have noted (including ChatGPT’s creators) how the chatbot often gives answers that make no sense or appear wrong. But the hits seem much more frequent than the misses, and overall the technology looks like it can already give better responses than the traditional tools we use when looking for our next meal.

I’ll have more to say on this later, but my initial test has convinced me that an AI like ChatGPT could significantly change the way home cooks and the food companies that serve us approach meal-making. While ChatGPT doesn’t have an official API yet, it probably won’t be long before it does. Imagine a world where a foodie-focused chatbot incorporates meal planning with a shopping engine and delivery to help you instantly build a meal plan and have it deliver everything you need to your door. I’m sure Google and Amazon are thinking about it, as are creators of dedicated recipe or meal-planning apps.

So will ChatGPT replace humans or other experts who help us make great food? Probably not, at least right away.

As for what ChatGPT thinks about that question, I’ll let you read its answer:

Food Tech News Roundup: Fungi Burgers, Pineapple Beer, and Chatbot Bartenders

Summer has descended upon us like a thick, laze-inducing haze. If you’re like us, all you want to do is head to the local pool and drink cool beverages out of our stainless steel straws.

Steamy weekends are not the time for more work, so we went ahead and rounded up some news-worthy food tech stories from around the web for your reading pleasure. Bonus: you can peruse while you’re lounging in air conditioning.

Bronx Brewery Beer Fights Produce Waste
On July 30th New York’s Bronx Brewery will release a beer made with repurposed food scraps. Called More To The Core, it’s a Kolsch style ale brewed with pineapple cores and skins, which are normally tossed into the trash and end up in landfills. This tasty, waste-y beer is a collaboration between Baldor Specialty Foods and The Bronx Brewery, and is available in their taproom.

 

Capital sprouts up for fungi-based meat company
This week Terramino Foods, a startup which uses fungi to make meat and seafood alternatives, raised $4.25 million in a seed funding round co-led by Collaborative Fund and True Ventures. In a press release, True Ventures indicated that Terramino Foods has already developed a plant-based salmon burger, and has plans to create alternatives to beef, chicken, and pork with its new capital. 

 

Costco partners with Zest Labs to optimize food supply chain
Wholesale giant Costco announced this week that it would start working with Zest Labs, a company which works in fresh food supply chain traceability. According to a press release, Costco is expecting this partnership to help modernize and optimize their fresh foods, reducing food waste up to 50%.

 

McDonald’s workers are short on soft skills
This week McDonald’s released the results of its Workplace Preparedness Study, which analyzed skill development across multiple age groups. The survey polled 6,200 people and discovered that many were missing soft skills, such as teamwork, customer service, and responsibility. We’ve addressed the restaurant labor shortage before on the Spoon, and have wondered if companies will pad their meager workforce with robots in coming years. But will robots have better soft skills than teenagers looking for a summer job? Or maybe the robots will take over the physically repetitive jobs, like food prep and dish running, freeing up people with soft skills to interact with customers.

 

Allrecipes & Tito’s vodka launch Barkeep, a chatbot ‘bartender’

Ready to get your drink on through Facebook? Allrecipes and Tito’s vodka got you covered. The recipe site is working with the Austin, TX craft vodka maker to launch a chatbot by the name of Barkeep using Facebook Messenger chatbot platform. After checking if the user is of legal drinking age, Barkeep suggests a few cocktails (using Tito’s, natch) and then walks the user through a conversation branch flow that has the user ultimately choose a cocktail recipe. Once a recipe is picked and the user is sent to Allrecipes, they can then order their some Tito’s or other liquor through Drizly. You can try Barkeep out for yourself here.

Did we miss anything? Tweet us @TheSpoonTech!

Wine-Searcher Builds Casey The Chatbot To Reach ‘Everyday Wine Drinker’

Since the time Wine-Searcher was founded by London wine merchant Martin Brown in the late nineties, the site has become one of the Internet’s go-to destinations to discover new wine. Over the past 18 years, the wine search engine has made a name for itself by pairing an extensive database of wines with the opinions of renowned wine experts like Jancis Robinson to help thirsty users find their next great bottle.

But if you just need to pick up a bottle for dinner tonight at the local wine shop or grocery store, you may not have time to sift through the millions of listings (about 9 million at last count) on the Wine-Searcher website or on their mobile app to find one. But that’s probably ok with Wine-Searcher, since nowadays they might just suggest you ask Casey.

Meet Casey The Chatbot

Casey is Wine-Searcher’s new wine chatbot. The bot, currently available in beta on the Wine-Searcher website or through Facebook Messenger, is a big strategic initiative for the company who sees Casey as a way to expand their addressable market.

“For us, (Casey) is moving us into the everyday wine drinker market beyond the wine expert,” said company spokesperson Suzanne Kendrick in a phone interview with The Spoon.

Kendrick explained the typical Wine-Searcher user ranges from wine enthusiasts who know enough to discern they “like New Zealand Pinot” all the way up to wine experts. However, the company feels there is a large swath of wine drinkers who just want a good bottle of wine and don’t have time to learn the difference between New Zealand and California Pinot.

Those drinkers just “want a recommendation, want a great wine at a great price, and they want to get it now and not wait for it to ship next week,” said Kendrick.

It’s for this consumer – the ‘everyday wine drinker’ – that Wine-Searcher built Casey.

Minimal Viable Product

The company has been working on Casey for about a year and has eight people working on the project according to Kendrick. To help them build the bot, the team has been working closely with Microsoft. That’s because the framework powering the bot’s ability to carry on a natural language conversation is Microsoft’s LUIS (Language Understanding Intelligent Service) platform.

According to Kendrick, the Casey is getting better and better and having conversations about wine, but she says the chatbot is still in the “minimal viable product” phase of development. While Casey is good at wine recommendations, it’s still learning to how to make food recommendations.

Casey, Wine-Searcher’s chatbot

I gave Casey a whirl, and it worked better on the Wine-Searcher website than in Messenger, where the bot told me the server was unavailable after I asked it for a $75 bottle recommendation to go with a hypothetical meal of fried chicken. On the company site, Casey asked me my wine preference (red, white, etc.) and price range and was able to recommend a bottle. When I chose a bottle of wine, it handed me off to Total Wine & More’s website for me to choose in-store or delivery.

This last part is important because Wine-Searcher makes much of its revenue through its relationships with large wine retailers like Total Wine & More. Other wine destination sites like the fast-growing Vivino, which just nabbed $25 million in funding, are taking more of a one-stop shop approach for wine buying by serving up recommendations and handing the commerce and delivery as well (it also looks like Vivino is working on its own effort to take its wine scanner capability from the app and put it into bot form).

For its part, Wine-Searcher is happy to stay out of fulfillment and shipping and just be the Internet’s wine experts helping the widest possible audience. With its chatbot, which the company is just starting to talk about, they hope to expand their audience and help take the company into its next two decades.

Conversational Cooking: Exploring Chatbots As a Cooking Interface (Podcast)

When I tell people I cook with Facebook, they give me a strange look.

But using Facebook’s chatbot as a cooking interface is surprisingly natural. The first cooking company to create a Facebook Messenger chatbot interface is ChefSteps, who launched their Joule-Messenger integration earlier this year.

The chatbot is part of the company’s larger vision around the idea of ‘conversational cooking’, which I discuss with the ChefSteps CTO Michael Natkin.

You can download this episode here. Make sure to subscribe to the Smart Kitchen Show on Apple Podcasts or wherever you listen to your favorite podcasts.

From Food Bot Discovery to Suggestions, Facebook Messenger Gets Smarter

From guidelines to making the perfect steak to numerous other conversational cooking applications, food-focused bots on Facebook Messenger have been advancing rapidly. Now, along with numerous other advancements, Facebook has launched new features that make discovering and trying new food bots much easier. At its F8 conference in April, the company announced new “Discover” features that would demystify finding an interacting with the best bots, and these features officially launched this week for users in the United States, along with new chat extensions that allow users to conversationally interact with sites such as OpenTable.

Messenger has more than a billion downloads on Google Play alone, and Facebook confirms that more than 1.2 billion users use Messenger each month. Its popularity is giving rise to an enthusiastic community of bot builders. The company has been adding chatbot  features within the nucleus of Messenger through its “M” AI assistant. We’ve written before about cooking with the Joule sous vide machine using Messenger, and new bots are taking conversational cooking in many directions.

So how do you discover the best bots and food oriented businesses and sites that you can interact with? On the lower right side of your Messenger home screen, touching a Discover button brings up categories that you can investigate, including one for Food & Drink. This lets you investigate organizations working with Messenger ranging from The Food Network to restaurants.

You can also investigate a “Featured” section to identify interesting new bots. A video from Facebook shows these features in action.

Bot developers and businesses can also now interact directly with users within Messenger chats. For example, you can reserve tables at restaurants conversationally via OpenTable. These features are enabled through Chat Extensions, which were also first announced at the F8 conference.

“Our goal with Discover is to ensure that experiences in Messenger are compelling, high quality and easy to find. This latest update makes it even more intuitive for people to find what they care about most,” writes Yingming Chen, a Facebook Messenger Engineer.

For developers and businesses interested in getting their bots or conversational cooking experiences added to the Discover section, submission instructions are found here.

Finally, Facebook has also made improvements to M, its AI-fueled personal assistant. As seen below, whether you are having a conversation with a person or a bot, M now intelligently suggests a “Save it for Later” option. If M senses that you are trading URLs for say, vegan recipes, it will automatically suggest that you save the links for later.  In addition to links M will suggest that you may want to save Facebook posts, videos and more.

Podcast: Robot, Meet Chatbot

In this episode, Mike looks at Andy Rubin’s new smart home platform, Essential Home. Rubin believes he can eliminate all the friction and fragmentation consumers face today with all the various platforms by focusing on integration. He’s created a smart home platform that plans to play nice with other platforms and hopefully get us out of a seemingly endless world of smart home apps and interfaces.

Our guest in this episode is Pawel Orzechowski, the Director of Systems Software at Neato Robotics. We talk about how Neato’s robots work with the smart home, how they are working towards new features and we look at why they decided to integrate their robots with a Facebook Messenger chatbot.

Make sure to subscribe to the Spoon newsletter to get it in your inbox. And don’t forget to check out Smart Kitchen Summit, the first and only event about the future of food, cooking, and the kitchen. 

MasterCard Sees Bot Applications As A Way To “Go Where Consumers Are”

We know the potential for the chatbot interface to be one of the defining stories of connected living in 2017 is there. Mike has covered the variety of ways that “social messaging chatbots” will impact the smart home and of course, the smart kitchen. MasterCard isn’t new to the smart home game – you might remember that they are the financial provider backing grocery ordering on Samsung’s FamilyHub smart fridge.

They’re clearly betting on bot applications as a way to encourage the easy use of their products on the Masterpass platform. Last week at Facebook’s developer conference, MasterCard announced a chatbot for Facebook Messenger, allowing customers to order from select retail and food vendors by chatting with the AI-powered interface. Similar to the on-fridge ordering partnership on the FamilyHub, MasterCard will work with Fresh Direct for chatbot grocery needs and also announced Cheesecake Factory and Subway for takeout food services.

MasterCard has prioritized chatbot integrations, releasing its bot API to developers earlier in the year. According to their developer site, MasterCard wants to make it easy to incorporate their “digital payment technology into conversational commerce experiences.” Beyond food ordering, the platform could be used to order from any retail partner in the future – giving Facebook an easy way to compete with online commerce giants and keeping consumers on the platform longer.

Masterpass-Enabled Bots

Facebook is increasingly interested in bot technology and sees its Messenger platform as a way for brands to reinvent customer communications and e-commerce. Facebook advertising, an increasingly popular way for brands to reach consumers by taking advantage of all the data Facebook collects on its users and serving them up personalized ads. Brands that advertise and have a large presence on the platform often use Facebook Messenger to communicate with customers, sending order and shipment information after a sale and answering questions. You can envision a future where as ad served up to someone who had recently been browsing for new shoes takes them to a chatbot that can offer custom selections and complete the sale right in the interface.

The opportunities in using natural language processing and artificial intelligence to communicate with us wherever we’re used to having conversations – whether that’s via text or in different messenger apps – are huge. Since Facebook introduced the concept, over 11,000 bots have been introduced on Messenger.

Whether it’s helping consumers cook their favorite recipe, ordering food or even communicating with their home, chatbots are definitely here to stay.

I Selected A Bottle Of Wine With A Chatbot-Powered Sommelier

About a week ago, NYC Media Lab held a demo day for a dozen new startup teams that graduated from the group’s twelve week “lean launchpad process”, a program which prepares the aspiring new companies to move on to “launch new products and services, participate in accelerator and incubator programs, compete for their next rounds of funding, and make their mark across a range of industries, including media and gaming, health, architecture and construction, and more.”

The companies represented an interesting cross section of ideas that include such technologies as virtual and mixed reality, haptics/wearables and AI. One of the startups focused on AI was VinoHunt, a team which bills its product as a “virtual sommelier” for those looking to imbibe.  As with each team that pitched during the demo day, VinoHunt presented their concept (a chatbot interface for selecting wine), their target market (people who like wine but don’t know much about it) and their business model (they take a cut from from each sale they assist with from partner wine shops).

One of the company’s founders, Ben Chang, presented where they saw themselves relative to both online and physical wine retailers and marketplaces:

Since I am a fan of using chatbot interfaces to help make food selections, I decided to check the company’s website out where I was surprised I could actually use their alpha stage product to help find a wine. I clicked on a button that took me to Facebook Messenger and boom, I was chatting with the VinoHunt chatbot.

While it’s clearly a work in progress not ready for commercial rollout (this was a startup demo, after all, not a launch), the overall experience was fairly intuitive.

It first asked me what I wanted to do. I told them ‘find a bottle’:

Then it asked me about delivery options and told me they currently only work with NYC wine shop Astor Wine (just remember: they made this clear in the demo, the team clearly didn’t expect a nerdy analyst type to actually find their product and use it). I said I’d pick it up at the store.

It then asked me what the wine was for (I said ‘pair with foods’) and then asked the type of food I was eating (meat):

It asked me what type of meat (fish) and then asked me my preferred price range:

It then surfaced a selection of wines which, at this point, seemed to be the same across the meat types (again, this is a demo).  What I did like is they also allowed me to get some info on the wine or request a tasting note. I asked for my details and it gave a nice description of the wine in a casual, descriptive format.

I then selected the wine and it took me to the wine retailers website.

While VinoHunt is the first Facebook Messenger powered wine sommelier I’ve seen, the company is one of many new efforts to bring AI to the world of wine. Companies such as Wine Ring, Vivino and even Google with their Google Assistant are developing AI-powered wine information products.

Long term, I expect to see an explosion in chat interfaces for applications like this. Like voice interfaces such as the one used for Google’s virtual sommelier ‘My Wine Guide’, chatbots make lots of sense for commerce-based decision making. As with voice, chatbots map well with commerce decision trees, but have the added benefit of being able to surface visually rich information such as showing the bottle of wine you may be about to purchase.

If you want to take an early tour of a work-in-progress virtual sommelier, you can check out VinoHunt here.

Why The Chatbot Interface Might Just Be The Smart Home Story of 2017

Voice interfaces are so 2016.

Not that Alexa and Google’s voice assistant won’t grow a bunch more in 2017, they will. But the reality is the smart home continues to evolve at a rapid clip, and one of the early trends I’ve noticed for 2017 is the emergence of the social messaging chatbot as a natural language interface for the smart home.

Credit Mark Zuckerberg for kicking off the trend in a big way at the end of 2016 when he debuted Jarvis, a personal growth project that the Facebook founder worked on for much of 2016. But Jarvis was more than just a skunkworks project, as the chatbot platform built into Messenger is gaining steam, including as an AI assistant for the smart home.

I recently used Facebook Messenger’s chatbot myself when I cooked steak with my Joule, and I was struck by how intuitive chat was as a command and interaction interface. While Joule is the first connected home device I know of to use the Messenger chatbot, I can certainly envision more devices that would work well with Messenger as the primary interface.

And if you’re more of a text message person than a Facebook Messenger user, don’t worry: text chatbots are coming your way as well.  As Lauren wrote this morning, a startup by the name of Unified Inbox is working with the likes of Bosch and Samsung to text-messaging based chatbots into the smart home as a way to work with their products. And while Yahoo’s text-messaging chatbot platform Captain is mainly focused on organizing communication with other family members, it’s not a stretch to imagine it as a control interface for our smart home.

While this trend is picking up speed, we should note that it’s not entirely new. Back in 2015, I wrote about how one of the biggest social messaging platforms in WeChat had started to integrate with smart home platform company Arrayent to utilize the messaging platform as an interface for products using Arrayent’s IoT platform.

While Alexa and other voice interfaces will no doubt continue their eye-popping growth this year, the reality is they are only one form of conversational interface for connected products. That’s why you can expect 2017 to be the year people starting talking about – and to – chatbots as a way to start controlling their things.

Alcohol Brands Turning to Chatbots for Creative Marketing

It seems chatbots are popping up everywhere in the food and beverage industry, and now they’re finding their way to the liquor cabinet.

Chatbots are applications that combine Artificial Intelligence (AI) and Natural Language Processing (NLP) to simulate human conversation.  They are an innovative way for marketers to reach out to target audiences and to support purchases.

As Allen wrote recently, chatbots are gaining increasing popularity as a way for grocery stores and restaurants to interact with target audiences.  Like food retailers, beverage brands, in particular alcohol brands, are quickly implementing chatbots as part of their marketing strategy.

Here is a look at what some top alcohol brands are doing with chatbots:

United Spirits Limited (USL), a Diageo Group Company, introduced Simi-Your Personal Bartender, a Facebook Messenger chatbot that provides bartending solutions.  Simi has a cocktail recipe catalogue of over 2000 recipes that feature Diageo’s brands, like Johnnie Walker Whisky, Smirnoff Vodka, Tanqueray Gin, and Captain Morgan.  With use, the chatbot will gain intelligence and offer cocktail recipes based on alcohol and ingredient preference.

According to B. Sridhar, VP Digital at USL-Diageo “There is a shift in the way consumers are interacting with brands today and through this conversational interface we wanted to build a first of its kind bar-tending solution that is not just cutting edge, but can also help us offer our consumers personalization at scale.”  The chatbot will be integrated across all Diageo brand pages on Facebook and the company’s lifestyle website, liveinstyle.com.

Johnnie Walker, one of the Diageo brands, is also rolling out, in addition to Simi, a digital education program that leverages Amazon Alexa skill, a messenger bot, and a Facebook Messenger chatbot.  The chatbot piece of their tripartite digital campaign is a guided whiskey tasting experience, aimed at giving whisky enthusiasts more knowledge. Johnnie Walker’s chatbot also offers cocktail recipes and enables users to execute on the recommendations provided, ordering alcohol and mixer supplies through Drizly or Cocktail Courier.

Free drink?

Vodka maker Absolut has launched its own chatbot, with the incentive of giving users a free drink.  Rather than providing DIY mixology advice, the Absolut chatbot leads users to the professionals—to bars where they can purchase an Absolut beverage, and redeem a special code for their free drink.  The responsible bot also gives drinkers the chance to get a ride home from Lyft.

As an official sponsor of the UEFA Champions League, Heineken is using chatbots as a way to get football (soccer) fans to watch the games by offering rewards like transportation and food delivery to viewers.  The Heineken Facebook Messenger chatbot will be launched in April.

So, why chatbots?

For one, alcohol brands find using chatbots are a good way engage consumers with recipe tools, bar finders, and interactive games. They’re also a good way to connect with younger consumers. Chatbots are particularly popular among Millennials, with research showing 60% of those aged 18 to 34 having used a chatbot at some point, according to Retale.

So next time you hit the bottle, remember you don’t have to drink alone. You can find company in one of the many chatbots finding their way to the local liquor cabinet.

Whole Foods Gets Into Food Tech With ChatBot And Meal Kits

Shopping at Whole Foods is going to get a little bit easier with some new expansions into food tech. The natural grocery chain unveiled a new guided recipe integration with Facebook messenger designed to make grocery shopping and meal planning easier.

ChatBot is Whole Foods’ first foray into the world of AI, but not into recipes themselves. For years the company published printed booklets, free to any customer, with pages of cooking ideas and suggestions based on the season and time of year. ChatBot is like a digital, smart version of those leaflets, responding to queries for recipes in Facebook Messenger with suggested links.

And the best part? You don’t even have to use words – ChatBot recognizes food emojis and throws out ideas based purely on pictures. Of course, beyond fruit, pizza and other random fast food items, you will have to inevitably use text if you want real help building your dinner plan for the week.

Whole Foods executive Jeff Jenkins told Venture Beat, “we are living in the ‘expectation economy,’ where consumers expect to have information at their fingertips, and we want to keep innovating to meet our customers where they are.”

In a quieter move following the ChatBot launch, Whole Foods hinted in their third quarter investment call that meal delivery kits is a strong area of interest and a product they plan to introduce in the future. Initially citing meal kit popularity as a point of competition for the company, Ken Meyers, Executive Vice President of Operations later stated that they are committed to the category and plan to reveal a full strategy down the line.

Meyers elaborated, “…with the creation of our culinary team led by Tien Ho, he’s now put together a really great group of leaders for us in the company. And it’s part of what we’re looking at with what we call our meal solution spectrum, which we’re really excited about because it’s going to address all aspects in which we want to bring food to our customers.”

It’s clear that traditional grocery stores are facing disruption from the food tech space and the increased investment in startups and non-traditional systems. With meal delivery on the rise and an increased desire for convenience, affordability and simplicity, it’s likely we’ll continue to see more big chain grocers using technology to bring customers through their doors.