TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Chatbots Don't Deliver Good Customer Service

137 点作者 rcymerys将近 8 年前

28 条评论

thanatropism将近 8 年前
Siri is not <i>essential</i>. Every time it fails to deliver a feature of my phone, I can thumb my way to it in seconds. So it&#x27;s actually fun whenever it works.<p>Also: because it&#x27;s not <i>essential</i>, one gets to adjust to its failures. There&#x27;s a broad range of queries for which I know Siri will just say &quot;this is what I found online for...&quot;; I tend to just open the browser and use Google&#x27;s autocomplete instead.<p>So... I have a problem when the chatbot is trying to perform an <i>essential</i> service, like getting a technician to come to my home because cable internet is not working. Imagine medical triage done by chatbots, jesus christ.<p>An MTV chatbot that tries to do interactive music recommendation? This could work. Spotify&#x27;s algo is already very good, but you can&#x27;t refine &quot;yeah, I wanted something more like X, but a little like Y. And not X exactly&quot; -- just &quot;give me more like X including lots of X&quot;.<p>And nobody gets hurt by a bad song recommendation.
评论 #14718924 未加载
computator将近 8 年前
&gt; <i>When you&#x27;re filling a signup form, you instantly know what information they&#x27;ll need from you. You can decide if you&#x27;re comfortable sharing them before you engage in filling it.</i><p>If only that were true! The trend is to ask for a little bit info at a time, then take you to the next page where it asks for other info, and so on. You don&#x27;t see at a glance the whole form anymore.<p>I resort to filling in fake info on sign-up forms, order pages, employment applications, airline&#x2F;hotel reservations, etc., just to find out what questions they&#x27;ll ask so I can decide whether to refuse before I tell them anything.<p>And also to find out key information they tell you only at the end (sales tax, shipping cost, etc.).
评论 #14719214 未加载
评论 #14718481 未加载
评论 #14722204 未加载
varelse将近 8 年前
I suspect what&#x27;s great about assistants like Siri, Alexa, and even Google Now is less that they have voice interfaces and more that they have well-funded support teams behind them to deliver exponentially more efficient routing of queries into appropriate knowledge-bases based on the best of contemporary research driven by their respective corporate thinktanks.<p>Compare and contrast with data mining the logs of call centers into RNNs and hoping for the best. A fun exercise here is to take one&#x27;s SMS logs and do the same. In my experience, one will achieve an amazing Max Headroomization of one&#x27;s cliches and trademark expressions, but little else.<p>When confronted with a voice menu system, I used to scream &quot;OPERATOR! OPERATOR! OPERATOR!&quot; at the top of my lungs and bang on the 0 key repeatedly until I got connected to a human. Recently, I&#x27;ve noticed they hang up on this behavior and even force one to wait through the entire braindead list of choices before allowing pro-users to bypass all the inanity because, after all, one must &quot;listen carefully as our options have changed!&quot;
评论 #14719616 未加载
评论 #14720229 未加载
评论 #14719260 未加载
api将近 8 年前
Chatbots, home IoT, and to some extent VR all strike me as things Silicon Valley wants to be &quot;the next big thing&quot; but are not and likely will not be because few people want them.<p>I absolutely despise chat and voice for any kind of trivial task. I want a UI. Chat and chat bots are annoying. Voice in any form if infuriating. Having to actually <i>call a number</i> on the phone for any reason always sends me into a minor little rage. &quot;Oh, you have to f&#x27;ing <i>call</i> for it... sigh.&quot; Why would I want more of this kind of experience? Maybe a few people do but I can&#x27;t see it being a Big Thing(tm).<p>I really do not want an Internet-connected fridge, stove, light switch, or microwave. When I buy such things I look for non-IoT-encrusted versions since those are going to be more reliable and are not going to be conscripted into a botnet or spy on me. IoT features in these kinds of products deliver nothing of value to me. I also really do not want DRMed food. That includes newer Keurigs. There is a healthy vintage Keurig market on eBay for a reason.<p>VR still seems like a fad or a niche product for certain subsets of gamers. There&#x27;s some market for it but it&#x27;s no &quot;E-Commerce,&quot; &quot;Social,&quot; or &quot;Mobile.&quot;<p>It&#x27;s sort of funny to see the SV investment culture producing so many solutions in search of problems after hearing that same culture lecture against this practice for decades. &quot;Do the market research first!&quot; &quot;MVP MVP!&quot; etc. They&#x27;re not following their own advice.
freehunter将近 8 年前
I run a Facebook page, and they&#x27;ve recently started pushing chats through Messenger every time you post something asking you to spend money to boost the post. Every single time. And if you do boost, they&#x27;ll beg you to boost again through Messenger. I tried &quot;stop&quot;, I tried &quot;cancel&quot;, I tried &quot;unsubscribe&quot;, and I even tried cursing at it to see if it would stop. It didn&#x27;t. Eventually I had to go into Messenger settings and block Facebook&#x27;s chatbot. I reported it as spam, since there&#x27;s no way to make it stop bothering you.<p>And now I see they&#x27;re automatically opening Messenger when you visit someone&#x27;s page to get you to message that business for... I&#x27;m not exactly sure what reason.
Rjevski将近 8 年前
The issue with customer service is that a lot of companies end up with awful CS because 1) they outsource it to braindead monkeys who hate their job and are paid pennies and 2) there is no way for someone to complete their task without talking to CS (no documentation, etc).<p>So instead of pouring endless money into chatbots, allow people to do whatever they wanted without involving CS. Provide good, up to date and easy to find documentation and a web interface if the task needs data entry (porting your number, changing your billing details, etc). This will reduce the load on your CS which means you can now bring this back in-house and no longer rely on an outsourced disgruntled workforce.
swiley将近 8 年前
If you can spend the time to write good documentation for your product then you don&#x27;t need a chatbot, just good search and good formatting.<p>If you can&#x27;t be bothered to write good documentation then you won&#x27;t be bothered to feed useful information into the chatbot, which is way more clumsy than a searchable manual anyway.
评论 #14722238 未加载
ejo3将近 8 年前
I use probably about 15 cloud SASS products for my company. Over the past year many of them have switched from offering either live chat or email support to chat bots. Often they will send out a marketing email pitching it as a huge improvement in support. My experience with chat bot support ranges from frustrating to infuriating, especially when I need help with something business critical.
评论 #14718107 未加载
ronack将近 8 年前
These are pretty well-worn arguments against chatbots. There&#x27;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&#x27;s possible just typing&#x2F;saying &quot;Send me a pizza with sausage and black olives&quot; is the most efficient way to order a pizza.
评论 #14718567 未加载
评论 #14718823 未加载
pavlov将近 8 年前
Chatbots offer a state-of-the-art user experience brought through a timewarp from the text adventure games of 1981.<p>&quot;You are in a maze of twisty little passages, all alike. There is a CUSTOMER SERVICE REPRESENTATIVE on the ground.&quot;
评论 #14718278 未加载
deegles将近 8 年前
I develop Alexa skills and I agree with the article. Another point that is missing is that the technology hasn&#x27;t &quot;closed the loop&quot;. We have great ASR and NLU available, but responses still need to be built by hand or templated. This is the major reason bots feel so unnatural. I think there&#x27;s a lot of opportunity for robust Natural Language Generation solutions to help build voice apps and chat bots that can operate more flexibly.<p>Also, there&#x27;s a need for a more declarative, high level programming language to describe how you can interact with a bot. Defining them as trees or graphs isn&#x27;t flexible enough. I&#x27;ve had promising results from experimenting with concepts from Ceptre (<a href="https:&#x2F;&#x2F;github.com&#x2F;chrisamaphone&#x2F;interactive-lp" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;chrisamaphone&#x2F;interactive-lp</a>). Fortunately there are a lot of startups experimenting in this space, I think we&#x27;ll see the most effective practices replicated quickly.
评论 #14718188 未加载
评论 #14719507 未加载
评论 #14718231 未加载
jaclaz将近 8 年前
Going a little sideways it&#x27;s not like at <i>any</i> Call Center you usually get to talk (without having first gone through all their standard &quot;script&quot; and possibly become upset and manage to escalate to a higher level of support) with someone that actually can provide you with assistance beyond what is already on the FAQ of the correspondent site.<p>(provided the site FAQ&#x27;s are actually frequently asked questions and not - as often happens - a bunch of questions that the original website developer jolted down because he&#x2F;she imagined they will be asked and that noone actually updates with &quot;real&quot; questions asked by customers).<p>So you get to talk with a human, but very often this human is either clueless or cannot really do anything about the issue at hand. (not of course fault of the human, but rather of the way he&#x2F;she was mis-trained or because of directives coming from the company)
评论 #14719819 未加载
评论 #14718364 未加载
sebslomski将近 8 年前
Chatbots are extremely hard. Many of us are jumping on the bot wagon and leverage AI with NLP &amp; intent recognition. But they miss the important bit: It&#x27;s all about the conversation itself. &quot;If content creation isn&#x27;t right, the conversation won&#x27;t delight&quot; (Adrian Zumbrunnen) The technical aspect behind chat bots is only the tip of the iceberg. We need Conversation Experience Designers instead of AI Engineers &amp; UI Designers. Many chatbots start with questions like &quot;how can I help you? Type something&quot;. What should I as a customer expect from the bot? When I visit a website, it&#x27;s pretty soon clear how it works and what to expect. This doesn&#x27;t apply to bots.
DustinOfDenver将近 8 年前
Great article! I have been working on my own Chatbot solution based on IBM&#x27;s Watson (supposedly cutting edge tech)... it is cumbersome... it cannot do something simple like extract a full address from a conversation (I think cities are still in beta)... The good news, there is a definite opportunity for some start up. AI is all the rage and for solving a specific problem with clearly defined parameters (or if you have a team of a few 100 people working on it) it is getting pretty good. But interacting with a human is many things... &quot;defined&quot; is not one of them.
romanovcode将近 8 年前
Wow, what a surprise. I&#x27;m only glad that some of them (for example Microsoft) allows you to request a human.<p>First thing to type when you get a chatbot support is &quot;I would like to speak with human&quot;. That usually works.
danieltillett将近 8 年前
Does anyone know of a single good chatbot? Every single one I have had the misfortune to interact with has been the best advertisement for their owner&#x27;s competitors that I know of.
olavgg将近 8 年前
Chatbots do work, those who say it doesn&#x27;t work have just tried the really bad ones.<p>Examples of chatbots that do work<p>Nuance&#x27;s Nina <a href="https:&#x2F;&#x2F;www.windstream.com&#x2F;Support&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.windstream.com&#x2F;Support&#x2F;</a><p>Jenn (unknown who is behind it) <a href="https:&#x2F;&#x2F;www.alaskaair.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.alaskaair.com&#x2F;</a><p>Our James <a href="https:&#x2F;&#x2F;master.boost.ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;master.boost.ai&#x2F;</a>
评论 #14718273 未加载
评论 #14718348 未加载
评论 #14718333 未加载
评论 #14718267 未加载
评论 #14718972 未加载
评论 #14719264 未加载
throwaway2016a将近 8 年前
Yet. Chat bots don&#x27;t deliver good customer service yet.<p>They will get better and eventually get better than humans. It&#x27;s a new use of technology, give it time to improve.<p>I already know of companies using AI to adapt to customers like this article says chat bots don&#x27;t do. It&#x27;s cutting edge but it is out there.
评论 #14718067 未加载
评论 #14718351 未加载
评论 #14719327 未加载
评论 #14718132 未加载
评论 #14719505 未加载
mercer将近 8 年前
So, in contrast to the article I personally feel excited about the potential of chatbots - especially as custom and user-friendly CLI&#x27;s&#x2F;UI&#x27;s more than as AI-driven &#x27;human&#x27; interfaces, at least for now - in a way I&#x27;ve not felt excited about anything in a long while (both from a business and ideological perspective, but I care more about the latter, all things considered).<p>I&#x27;d just like to ask that if anyone is seriously pursuing chatbots, beyond just helping businesses or consultants sell the &#x27;next big thing&#x27;, I&#x27;d really, <i>really</i> love to talk. My email address is on my profile page.
pmontra将近 8 年前
I agree with the conclusion. Voice input instead of text and better understanding and language generation would help.<p>However the current status is not so grim. In a different application domain, a customer of mine uses a chatbot to collect leads of credit requests. Their very basic chatbot converts much better than their form. The difference is so big that it pays for the extra work to manually extract data from those conversations that went to the end but we can&#x27;t automatically get all the information from (funnily formatted dates, addresses, etc)
gidim将近 8 年前
Yep chatbots sucks. The trick for good customer support is to enhance a human agent with AI and not trying to replace it. Suggesting answers to the agent and automatically replying when the confidence is very high.
vkou将近 8 年前
To the surprise of nobody who has ever gone through automated telephone system hell. Whenever I bump into one, I impulsively shout &#x27;zero&#x27; &#x27;zero&#x27; &#x27;fucking operator&#x27; into the phone.
评论 #14719570 未加载
danjc将近 8 年前
Zork. In 1980. An example of a text interface that worked better then 99% of chat bots today. Chat is not a bolt on, it&#x27;s a product in its own right.
dyeje将近 8 年前
Funny to read these comments when not so many months ago chatbots and conversational UI were all the rage.
评论 #14718300 未加载
mmartinson将近 8 年前
I&#x27;ve been spending a good part of a last year working on a chatbot with a very domain-specific scope, with that goal of arriving a product that delivers a modest but effective user experience. It&#x27;s hard and it takes an unbelievable amount of work to handle myriad of edge cases you get into when a human on the other end tries to treat your bot like a real albeit limited interlocutor in the conversation.<p>The real problem I see is that the last decade of user experience improvements that work well on the web don&#x27;t really translate into a chat, as an industry we&#x27;re hopelessly bereft of best practices at this point, and our users notice this and experience it as the frustration of having no idea what to expect from a bot. The title article and comments cite a lot of good examples.<p>NLP and other applications of machine learning will make bots better at delivering correct answers, but making bots feel not-horrible around the edges is about user experience design. Here are some suggestions that have helped me a lot.<p>* Design for failure first<p>Just like mobile-first design gets the brain out of the pattern of tacking on mobile interactions as second class citizens, failure-first design focuses on the primary experience the users have of your bot, it not working. Don&#x27;t delude yourself into thinking that your NLP intent parsing is going to result in more hits than misses down your happy path to user delight. A human will always sidestep your intended flow by accident, and that human will form judgements about your product based on it&#x27;s ability to gracefully recover. Luckily the bar is incredibly low here.<p>* Be careful with conversational niceties and over-humanization of tone<p>It&#x27;s easy to think that friendly banter and emojis can help personify a bot and smooth over the above-mention failure paths, but the novelty of these wear off quickly for a user, and the user is likely to experience more frustration if the conversational tone doesn&#x27;t match their frustration. It is also extremely easy to end of in the uncanny valley when using friendly conservational copy in the bot messages. Repetition of a robotic message feels benign-if-annoying, but repetition of a cute emoji-laden phrase can feel very off-putting.<p>* Fall back to being a CLI with visibility and helpers<p>If you&#x27;ve ever been stuck working with a bot, you know that all you want is to know what it can do, and how you can get it to do that thing. If you notice the user is in a failure state through keyword matching or repeated failed routing attempts, fall back to a high-visibility list of actions. Having quick-action buttons can make this even smoother.<p>* Train the user on consistent hooks and keywords.<p>When speaking in a human conversation, utterances of &#x27;stop&#x27; or &#x27;wait&#x27; are almost always respected as context-independent keywords that escape or pause the context of the conversation. If I asked you what you wanted for dinner, and you responded &#x27;stop&#x27;, I wouldn&#x27;t try to figure out what kind of food that was. In my project, &#x27;help&#x27; &#x27;quit&#x27; and &#x27;back&#x27; are all respected as keywords, and every context of the conversation implements callbacks to respond in context to each of these.<p>* Ask a lot of questions that are easy to answer<p>Handling raw language is super hard. Routing language into a finite set of options is a lot easier, plus humans feel listened to when asked for clarification or if they have been understood correctly. When taking user input and routing to an action, ask for yes&#x2F;no confirmation, and provide options like &quot;This is totally wrong&quot;. Opportunities like this could be great to collect data about how users are stuck to improve on the experience. It&#x27;s also validating for the user to feel like they can specify that they were not heard correctly.
bryanrasmussen将近 8 年前
anyone have some statistics&#x2F;research on how badly chatbots perform in delivering services?
yebsido1将近 8 年前
no one can seriously like chatbots
KirinDave将近 8 年前
This article is... weird. It basically assumes the Facebook pseudo-menu-driven chatbots people fat-finger into their systems with almost no consideration for UX are the state of the art.<p>It then compares it to a personal agent that actually has a similar model and the <i>worst</i> voice recognition and search precision of the current crop agent software which... isn&#x27;t even really the same kind of software?<p>What is this article even trying to say? Poorly written bots are bad, well-written agents are good, and voice interfaces aren&#x27;t as bad as people make them out to be?<p>Cool.