Live data from Hacker News

Chatbots: Still dumb after all these years

mindmatters.ai

1–10 of 426 posts

Re: Chatbots: Still dumb after all these years

#3
Yet another Next Big Thing that I was right about predicting would fail. The problem I saw was lack of discoverability. This is also a big problem for voice assistants. About the only thing we use our Alexa for is kitchen cooking timer and voice activated jukebox.

Re: Chatbots: Still dumb after all these years

#4
post #3

Yet another Next Big Thing that I was right about predicting would fail. The problem I saw was lack of discoverability. This is also a big problem for voice assistants. About the only thing we use our Alexa for is kitchen cooking timer and voice activated jukebox.

>Yet another Next Big Thing that I was right about predicting would fail.

I was hired at my current company 4 years ago to work on our chatbot client. Despite years of engineering effort put into an NLP based decision tree system, over 90% of chats were still falling back to a live agent. They just recently sunsetted the product for lack of interest. Thank god that fad is over. Web design trends come and go, but that was by far the most obnoxious one yet.

Re: Chatbots: Still dumb after all these years

#6
Despite the rudimentary nature of the sophistication of chatbots even today, they have always been an amazing source of entertainment for me and others in group chats. Back in the late 90s and early 2000's they were a great addition in casual IRC channels, with some slight tweaking so they don't spam the channel (important!) but enough that they would occasionally speak up on their own and could be engaged directly at any time.

Some of my best memories of conversation in IRC revolved around some of the ridiculous content that the chatterbots would come up with, especially if the bots started arguing with each other. It was such a great source of background content during periods of low activity.

Re: Chatbots: Still dumb after all these years

#7
Good points. But language models are usually then fine-tuned for specific tasks. Contextual reasoning in NLG is a specific area of research that attacks some of the points raised and certainly BERT wasn't pretrained to solve all tasks in NLP/ NLG area of research.

Re: Chatbots: Still dumb after all these years

#8
post #4
post #3

Yet another Next Big Thing that I was right about predicting would fail. The problem I saw was lack of discoverability. This is also a big problem for voice assistants. About the only thing we use our Alexa for is kitchen cooking timer and voice activated jukebox.

>Yet another Next Big Thing that I was right about predicting would fail. I was hired at my current company 4 years ago to work on our chatbot client. Despite years of engineering effort put into an NLP based decision tree system, over 90% of chats were still falling back to a live agent. They just recently sunsetted the product for lack of interest. Thank god that fad is over. Web design trends come and go, but that…

I got the impression the entire thing was pushed by Slack probably by way of some PR firm.

I utterly despise how mindlessly faddish this field is. For a field supposedly so full of smart people who often pride themselves on being "contrarian" (sometimes to a fault), people sure do bleat like sheep when the next fad comes along.

Re: Chatbots: Still dumb after all these years

#9

I really hate when companies hide behind chatbots. Like, NOOOO, your "AI" chatbot didn't help me - get me an actual person.

It can be quite useful in a weird way. While everyone else is stuck on the chatbot going round in circles, usually typing something like "human" or "talk to human" will make the chatbot connect you with an actual human representative (or ask you a few basic questions first and then connect you).

I've used the trick on various large company's websites when trying to get support and it seems to be quite 'universal'.

Post reply on HN