These are pretty well-worn arguments against chatbots. There's an overuse of bots for tasks that do not benefit from a conversational interface (checking the weather, surveys, promotions, etc.). But if you stop thinking of bots as sentient beings and instead treat them as domain-specific command line interfaces, you may get more utility out of them. For instance, it's possible just typing/saying "Send me a pizza with sausage and black olives" is the most efficient way to order a pizza.
I'm surprised with the sentiment on HN about this.
Chat bots promises the power of the command line without the learning curve.
That is something to be exited about!
I'm not impressed by the Pizza example either. In my experience ordering via Justeats app or website is ~30min longer than just calling the shop. In fact, I will sometimes use JustEat to look at the menu and then call the shop to save time.
Chat is obviously slower at typing than talking, but the tap-speed when typing simply cannot be compared with tapping through menus.
It's so much easier to fill out a form than it is to talk to a human. I read faster than most people speak, and I can scan and review much faster via sight rather than voice. Talking to someone is valuable if I have questions or there is some uncertainty. Assuming that I know what I want and have no questions, it's much easier for me to order food online than to call a restaurant.
Chat bots can only really search a database of documentation and frequently asked questions. Making one that has the benefits of talking to a human might be tantamount to AGI
This is why I'm very skeptical of this current craze for chat bots. It seems to me that they're really only useful if they can infer a wide range of intent from the user's input, and that seems like it's still very much an unsolved problem. Otherwise they're just glorified menu systems.
You know, there is at least a dozen chatbot providers who can handle these nonstructured dialogues with multiple entry points, ESPECIALLY with pizza.
In fact, the pizza order is the No. 1 scenario looked at by the chatbot providers.
In fact, it was exactly the scenario my old startup took as a case study and the first application we built with it. It could handle the different toppings, the sizes, and more. You could submit all your requests in one move, it would be parsed and sorted into its little slots.
The problem? There is only a handful of scenarios similar to the pizza. In most cases in the real world, you have to select from an external database, look at proprietary product names, and more. Another staple of chatbot demos, plane ticketing, only works well when limited to North America (in the English word). Good luck asking for a flight to Kinshasa, Kuala Lumpur, or even Wagga Wagga in Australia.
I am not even talking about the switchboards for multiple domains, like in Alexa. These ones only work with "leaky abstraction" (making the user learn magic keywords).
Another problem is really stupid. It's the availability of the datasets. The funny thing is, ye olde style semantic frameworks fare better than the machine learning ones, because there is not enough data for the machine learning chatbot frameworks, and without it, their mighty capabilities are pretty much the proverbial spherical cow in vacuum. But because the semantic paradigm is not kosher/kewl anymore, very few enterprises agree to deploy it.
None of that matters though because the users never liked typing a lot. Back in 1980s - 1990s the adventure type computer games switched from (mostly working) command line interface to point-and-click, and very few users objected.
My take is, the key is a conversational UI with strong visual feedback. For the pizza scenario above, I would draw icons of cheese and numbers, so that the user can be sure it worked.
I think there are multiple facets to this argument (both for and against). Yeah, a lot of chatbots are so "stupid" or at least so obviously non-human that as a user, I have absolutely no desire to interact with them. They waste my time and I end up doing the same thing as I sometimes need to do with automated phone systems: press the virtual equivalent of "0" to try to get connected with a real human.
But that is starting to change: some chatbots can now start understanding and interacting like humans. As a user, when that's the case, I don't personally care what is powering the thing behind the scenes. In fact, I'd generally prefer a bot if it's as good as a good human: the number of times I've had 45 minute or longer sessions with some human support agent that:
1) Just didn't listen to what I was looking for
2) Had difficulty communicating because I started a chat on an evening/weekend and got routed to someone who had English as a second language
3) Couldn't actually figure out how to solve some problem, so I had to start a new conversation of the same substance the next day
4) Didn't actually log the notes of my chat for the next agent, so I had to repeat myself
etc
is just completely off the charts and it's anecdotally gotten worse in my experience in the past few years.
I totally agree with you here. The use of a chatbot becomes advantageous when the cost of delivering intelligent responses is prohibitive in terms of quality and / or speed.
Absolute. I wish engineers could use better examples to explain capabilities.
Ordering a pizza as shown in the above example is very contrived, no one needs that, a GUI is much better to execute this use case. But the power of chatbots will light up if it can answer 'Would this pizza be too spicy?", "can you deliver this after 4pm?". What I mean is when the chatbots can take over more of customer queries which otherwise might be directed to the store via phone call. Or something which requires deep knowledge of the product and when not every corner case can be put on the GUI menu.
I've never had a good experience interacting with a chat bot. I find it insulting when a company I'm already giving money to insists I talk to a robot before I get to talk to a human being. Chat bots are just the latest version of listening to a dial in support phone menu and trying to figure out which option you need.
I think it's equally wrong to just write off chatbots. They are a User Interface tool that works in some areas and doesn't in others (and recently has been dramatically misapplied).
Chatbots work well as an input when your hands are otherwise occupied:
- driving/directions (Google Maps telling you where to go)
- cooking (reciting a recipe)
They work well when you're requesting a specific thing:
- "Play Everlasting Light by the Black Keys"
- "Add Eggs to my shopping list"
- Responding to Answers in Jeopardy: "What is Syracuse?"
They can work as an alternative CTA in certain narrow areas where they function like a traditional "wizard". I've seen some ecommerce stats for things like "Are you shopping for a Fathers Day Gift? Does your dad like sports? Does your dad like gadgets? Want to see some popular gift ideas?"
Where they don't work:
- complex NLP dependencies
- data entry
- when there is an expectation set that you're talking to a human.
Chatbots are great if they assist me with quick actions, like viewing my order/shipping status, and when it's obvious that I'm "talking" to a bot. What gets annoying are chatbots that start with "how can I help you?" and attempt to use natural language processing on my reply to guesstimate a response. More often than not I end up frustrated, wishing there was an 'Operator' button that I can use to talk with a real person. It's way easier and more comforting to be talking to a real person behind the business when I need something.
It's distressing that more and more chatbots are spawned every day to take the human element out of customer support or when engaging with a business. Chatbots work when they're a complement to human customer support, but when they're up front and center they tend to be distracting, frustrating, and their attempts to act human often amuses me. I do like Kik's and Messenger's approach to a bot and I think they are on the right path.
Has anyone seen some top-notch chat bots recent to the restaurant space for helping people do phone orders? Some people here describe uses of chatbot that are meant to basically thwart customers and waste time, but IMO chatbots are getting good enough to eliminate some customer service roles.
In some ways they are great because they make command line more popular in some ways the are completely useless as they turn something which should most likely be automated into a manual process.
We at Microsoft think about bots as somewhat "intelligent", as in - they understand your intent. There's a little example chat with a pizza bot: It's a subtle difference, but being able to have a conversation vs navigating a flow chart is pretty powerful for a bunch of applications.
That the key point for me. If the chatbot can’t act on the system for me beside « get me human », it’s useless.
I like them when :
- it can schedule a call back with a human
- it can open ticket, ask for document on my side and make it faster for my query to process overall.
Most Chatbots I know are just an interactive search for a website/documentation. If it works, good, saves the trip to google; if not, I can still ask the bot for other ways to communicate. Why bother with a human when when it just costs more time?
Chatbots are like IVR systems and phone trees. It's a neat idea, but they are a pain in the ass, nobody likes them, and their benefit over a human is marginal in a best case scenario.
> Chat bots work best where users already are. If your users are primarily spending time in messaging platforms where bots and micro-apps can be seamlessly embedded, great.
Fully agreed with that. While for sure "boring" for many and not good as marketing tools, the best "chat bots" IMHO basically are inline commandline tools that help specific communities.
I actually work on a chatbot for a big company [1], and I feel like chatbots are substantially better when they are more targeted and less conversational. For example, I'm perfectly happy to use a chatbot and type "return something", since that's relatively easy to parse correctly, and once you're in the right flow it works just fine.
Where I feel like chatbots get bad is when they try super hard to fool you into thinking you're talking to a human. At that point, I totally agree, just give me a human.
[1] It's probably not too hard to find out which company, but I do ask that you do not post it here if you do.
reply