Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Chatbots: Still dumb after all these years

mindmatters.ai

Post reply on HN
Print view View original

191–200 of 426 posts

Re: Chatbots: Still dumb after all these years

#191

Post by Teandw »

tetha wrote: post #93
dexwiz wrote: post #45

Chatbots are about as useful as phone trees. They can help solve the top 5 easy/common problems, but they are useless passed that. Anyone who has worked in a call center knows that more than half the calls are about the same couple of issues: reset password, finding common help docs, etc. Since help desks are cost centers, it makes sense to half a robot handle as many of these as possible. I think most of the hate di…

This is what our NLP teams are indeed working on. Sales prefers to describe it in more colorful ways, but practically, they are developing a more natural interface to an initial decision tree - you don't press 5 for a connectivity issue, you type "My fritzbox doesn't internet anymore" into a chatbox and it recognizes that as a connectivity issue. This goes on for 3-4 questions, until it either generates a case a huma…

Is the 5-10% savings on agents handling phone calls worth it when reputation damage is taken into consideration?

Re: Chatbots: Still dumb after all these years

#193

Post by scotty79 »

Just try to use GPT3 as a chatbot. It will blow your mind.

Sure, it thinks it's 2017 and knows nothing about covid and if you ask it to explain math to you it will serve you pure garbage in most educational tone and manner, but it keeps context of the conversation orders of magnitude better than anything else.

It doesn't feel like a bot. More like a dumb and confident human.

Re: Chatbots: Still dumb after all these years

#194

Post by Phelinofist »

klyrs wrote: post #12

My favourite flaw of chatbots is exposed by ELIZA. Not chatting with ELIZA, (though, it does suffer this flaw) but using responses inspired by that program. "Please elaborate on that" or "tell me more about [noun]" etc. Bots appear to have zero lines of short term memory, and utterly fail to pick up a reference to the thing that they just said. My favorite being bot> [something plausibly human-sounding] me> What do y…

Two months ago I started working at a company that develops the new speech assistant for a large German car manufacturing group. The assistant will support such queries pretty well. [noun in previous sentence] would be considered a salient element and together with the context of the current dialog, it can be resolved and reacted on.

Re: Chatbots: Still dumb after all these years

#195

Post by klabb3 »

version_five wrote: post #42
pwinnski wrote: post #13

Having worked in ML at two different companies now, I think that people interpreting model output as intelligence or understanding says much more about the people than about the model output. We want it to be true, so we squint and connect dots and it's true. But it isn't. It's math and tricks, and if human intelligence is truly nothing more than math and tricks, then what we have today is a tiny, tiny, tiny fraction…

I think a problem is the tighter cycle between academic discoveries and business people trying to monetize them. Large language models were developed, objectively a great achievement, and immediately someone nontechnical wants to apply their own interpretation and imagine that we can build a chatbot that you won't have to pay, and before you know it, people are selling and even deploying them. Anyone who questions or…

> Anyone who questions or points out that the technology doesn't do what the business people think it does[...]

Uh oh, we've got a downer!

Jokes aside, I'd like to consider an even simpler explanation, namely that "The purpose of a system is what it does"[1]. In this case, it would suggest decision makers are fully aware that they suck. Why would anyone want something that sucks? Because it's discouraging, and customer service today is all about discouragement. Unsubscribing, replacements, returns, special requests are all costs, and that's a fixable problem in the current business doctrine, especially in the faceless megacorp flavor of business. While chat bots (and other dark patterns) are frustrating, it creates a veil of plausible deniability for the business. It's hard to claim that it's deliberately hostile to customers, even though it's the simplest explanation.

[1]: https://en.m.wikipedia.org/wiki/The_purpose_of_a_system_is_w...

Re: Chatbots: Still dumb after all these years

#196

Post by arendtio »

I don't think there is so much of difference between labeling and understanding things. I mean, we humans don't even understand ourselves and yet we tend to use our intelligence as the general measure of intelligence.

But if labeling is enough, what is missing? The current approaches are mostly based on single dimensions, like pure text, images, sound etc. but rarely a combination of them. So when a human, who lives in a world where images, sounds, physical experiences, emotions and abstract information have to be combined meets an AI that lives in a single dimension it is easy to see the blind spots.

So maybe just giving machines access to all the dimensions we humans perceive might help to let them act more like we do.

Re: Chatbots: Still dumb after all these years

#197

Post by jazzyjackson »

hotpotamus wrote: post #23
klyrs wrote: post #12

My favourite flaw of chatbots is exposed by ELIZA. Not chatting with ELIZA, (though, it does suffer this flaw) but using responses inspired by that program. "Please elaborate on that" or "tell me more about [noun]" etc. Bots appear to have zero lines of short term memory, and utterly fail to pick up a reference to the thing that they just said. My favorite being bot> [something plausibly human-sounding] me> What do y…

I'm not trying to be mean or break any HN rules, but did you read the article? It basically covers what you asked and was quite a revelation to me. Others in here point out that GPT-3 is not a chatbot which is good info, but I also wonder if there is anything out there that can even "remember" the context of a conversation it's supposed to be having. Particularly interesting is the question from the article, "who is…

"chatscript" is a great dialogue engine where language patterns land the state machine into a "topic" which it gracefully backs out of (keeps a topic hierarchy) when it runs out of responses in that topic / branch of conversation.

It also includes the most robust, hand-tuned lemmer and stemmer + disambiguation language parser built on top of WordNet. really good stuff, written in C so its light on memory and responses are instantaneous.

https://github.com/ChatScript/ChatScript

Re: Chatbots: Still dumb after all these years

#198

Post by tombert »

voiper1 wrote: post #173
tombert wrote: post #121

Earlier quoted context omitted.

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 thi…

If it's something direct like "return something" then what benefit is there over using the website's interface? Is it just this interest in doing everything by whatsapp?

> If it's something direct like "return something" then what benefit is there over using the website's interface?

There's no "benefit" exactly, the item gets returned the same way regardless, but it's kind of nice that it's consolidated. The chatbot works as a bit of a "one stop shop" for a lot of administrative stuff like "where's my order" or "return something" or "my order didn't go through", stuff like that.

AFAIK we don't support doing anything through Whatsapp, just our site.

Re: Chatbots: Still dumb after all these years

#199

Post by CRConrad »

semi-extrinsic wrote: post #138
dkarl wrote: post #100

Earlier quoted context omitted.

There isn't really a new "problem" with AI. Businesses love hype, they love anything that can punch up a sales pitch, they love shitty cheap automation that replaces expensive human work, they love to identify ways to lower quality and save money without affecting revenue, and AI can be good for all of those things without being good at anything.

No, but most chatbots I've seen are no better than a well-structured FAQ page. We've had those since the mid 90s.

> No, but most chatbots I've seen are no better than a well-structured FAQ page.

For people who can't be arsed to glance through a FAQ, they're kind of an iterative natural-language query interface.

Re: Chatbots: Still dumb after all these years

#200

Post by shrdlu2 »

Having worked on conversational AI (virtual agents/chatbots) for over a half a decade now, I can say that there are large differences in the capabilities of the solutions and the quality of implementations. Some are just bad and unhelpful. Some are very good. I'm personally familiar with several voice deployments doing millions of calls a month. Not only are there obvious cost savings but the calls handled (entirely) by the virtual agents get better average cust sat metrics than human agents on the same set of calls. The first time I saw that I was surprised, but, now it is pretty typical. They absolutely can be helpful even if they are still not near to passing the Turing test.
Post reply on HN