I was an undercover bot for 2 months
medium.comI can't help feeling there's a "walking before you run" thing here. Unsurprisingly, no, you couldn't make something to do this yet. Because we haven't yet built anything that passes the Turing test.
But the fact that we can't yet do that doesn't mean that bots are going to be useless. That'd be like looking at the first ocean-going freight vessels and saying "well, it can't move 300,000 tonnes of freight, so it's useless), or the Wright Flyer and saying that because it can't cross the Atlantic, it's a bit rubbish. (I'm aware this is close to straw manning, but bare with me...)
Sure, early proofs of concept are often both limited in scope and fairly dire. But that doesn't mean there's no potential utility in them and what they do. I suspect bots are similar. Initial, narrow use-case versions will be very useful at providing value in specific circumstances, and eventually they'll become more general in nature. But decrying them at this stage seems a bit like throwing the baby out with the bathwater.
I realize this is not related to the actual article, but having looked at their website (http://www.workgroup.im/) this really struck me.
Does anyone else find it a little bit gross when companies take stock photographs, give them a name and write stories about how they use the product? It's clearly meant to work as a social proof and to look almost like an endorsement from a peer.
It's just another warmer, fuzzier dark pattern in my opinion.
It's especially jarring because their photo of "James Gold" is actually my coworker http://andymatthews.net/
Are you sure your coworker isn't actually a stock photo?
Yeah, the way they are doing it with stock photos and made up personalities is a bit off-putting. I definitely prefer when they make it obvious they are describing use case scenarios by using names like "Freelancer Fred" and "Associate Annie".
It kind of makes you wonder if this whole article is just PR/advertising to say "look at us! no bots! personal touch!"
Totally agree - if I didn't look specifically for what you're mentioning, I would have certainly taken it as real people giving endorsements and scrolled on.
I was about to be charitable and say 'maybe those are LinkedIn pictures,' but all it takes is a Google image search to verify that, indeed, they're stock photos.
Seems like we haven't progressed much beyond Clippy, the old MS Office "bot" from 1997. So perhaps we shouldn't be holding our breath. (Though AlphaGo just came out of nowhere so....)
I guess something that wechat does is more appropriate for the time being to use in business products... If at all.
http://dangrover.com/blog/2016/04/20/bots-wont-replace-apps....
I found it interesting that many of the text UIs wind up with a list of numbers to type for each command. This is the exact UI everyone built when I started programming in the early 80's.
Previous discussion about this link: https://news.ycombinator.com/item?id=11557166
I have a hard time giving credit to the examples they raise, since they say users were aware that humans were present behind the 'bot', which would explain to me why they used emojis / gifs and images to talk with the 'bots'.
Can a bot be made which understands emotions, sarcasm, etc.? Can something be made which does more than just parse commands and gives out predefined replies? If so, how far away are we from this?
You're asking whether we can create artificial intelligence.
General artificial intelligence with a knack for natural language, that is...
Bot can be made where one doesn't have to parse commands.
The author of the article could have collected all the conversations and learned a bot that would correctly converse with people asking similar questions.
there's no reason that having the same question asked in different ways should be a problem.
language is structured. structured learning and prediction exists for more than two decades and just recently there have been very nice improvements to known methods (learning to search, neural networks for structured learning etc.).
one can try to summarize an answer to a question from relevant fetched documents. summarization is a structured prediction task.
for example, in the conversations with a bot, you store all of the questions and your answers.
your answers were formed by using documents that contain the needed information. now you're trying to find a mapping that will successfully fetch the relevant documents for the question, and then summarize all of the documents to as close as possible summarization (summarized text should be similar to your stored answer).
structured prediction techniques use simple methods such as pos tagging and then pruning the dependency parse tree of sentences in document to shorten it, excluding whole sentences or text-between-commas or unneeded-adjectives etc. (these methods are based on statistical machine learning, not some silly rule based technique, one can incorporate word2vec features or other neural network magic)
it's not impossible, given enough data, to build a bot that would interact successfully.
sarcasm, and emotions are still a bit away, mostly because they require knowledge about the world, and if your world is a small set of documents you won't successfully get the sarcasm or emotions. this is also the case with people when they come to a different culture.
Would have loved to see some data on what requests were easily handled by the bot and/or what questions could truly be answered by a fully automated bot.
I don't think they had a actual bot at all.
Right, so what I want is a list, or even anecdotes of requests made that could have been handled by a bot. All we saw were the opposite examples, of queries not able to be processed by a true bot.
Literally just a man behind a curtain