[HN Gopher] Chatbots: Still dumb after all these years
___________________________________________________________________
Chatbots: Still dumb after all these years
Author : zdw
Score : 396 points
Date : 2022-01-06 16:27 UTC (6 hours ago)
(HTM) web link (mindmatters.ai)
(TXT) w3m dump (mindmatters.ai)
| Barrin92 wrote:
| after having played AI dungeon for a while these issues become
| obvious very quickly. These large models are good at producing
| text in some probabilistic manner but they don't understand
| anything at all.
|
| Other than for obvious commercial and hype reasons I have no idea
| why there is still so relatively little recognition of criticisms
| that Gary Marcus and others provide because it's blatantly
| obvious if you interact with these systems even for a few minutes
| that they're to intelligence what a trojan horse is to a real
| one.
|
| There's no real understanding of the world, no coherence, no real
| ability to grasp logic or have some ontology of the world and
| that makes reasoning about the world other than producing some
| 'nice sounding BS' as the article puts it impossible.
| darepublic wrote:
| I think useful chatbots are still in the cards for the next
| decade. But yes so far our exposure to them has been uninspired
| landing page support plugins.
| bozzy wrote:
| 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.
| mike00632 wrote:
| I had a positive interaction with a chat bot yesterday that
| serves as a good example of what you describe. My home internet
| had an outage and I went to my cable company's website to
| report the incident and perhaps get an ETA of when it will be
| restored. I interacted fully with a customer service chat bot
| which handled the whole situation flawlessly.
| maxdo wrote:
| Author don't understand the difference between chatbot and
| general intelligence. Chatbots made huge progress in the last 3-4
| years helping businesses and people. But they have nothing to do
| with topics in the article.
| banana_giraffe wrote:
| In the early days I worked at a company that had a natural
| language chatbot product. It wasn't an online thing, but rather
| part of a larger tool. You could ask it to do things like "show
| me the quarterly spreadsheet", and if it didn't know what
| "quarterly spreadsheet" was, it'd ask questions in English and
| learn what "quarterly" and "spreadsheet" meant. And it could use
| that new knowledge to update its questions so if you asked for
| "spreadsheet", it would know to ask if you wanted the "quarterly"
| one, and so on.
|
| This was in the long ago, so it wasn't ML, but a very large state
| machine written by someone that was no doubt a genius, and also
| had no coding standards to speak of. Updating it was a maddening
| process, and thankfully one I rarely had to think about since I
| was tasked with GUI stuff.
|
| When I was hired, I was told it was a fantastic app, customers
| loved it, and so on. Later, when I was talking to support reps
| one day over lunch, I learned that the number one activity they
| had to do was log into deployments remotely and remove
| "knowledge" from the state machine of new swear words the
| customer had taught the machine out of frustration trying to get
| it to do something, which caused this feedback loop of the
| interaction swearing at users.
|
| I often feel like we're not in a better state these days.
| brettdeveffect wrote:
| What you are describing counts as ML.
| namdnay wrote:
| Yes it's literally a machine that learns!
| rcoveson wrote:
| Sounds like it should have kept track of who taught it things,
| like a child.
|
| "Here's your fucking spreadsheet"
|
| " _gasp_ Who taught you to say 'fucking'?"
|
| "It was George in Accounting Employee ID #3728917"
| banana_giraffe wrote:
| As I recall, it did keep such records, if for no other reason
| than there was some degree of personalization that went on.
| The people higher up the food chain tended to be the ones
| that taught it more clever words and phrases.
|
| My memory's fuzzy on the finer details, but I do recall a
| "bad words" list of things it would ignore in human input
| hardcoded somewhere. But of course, that just meant people
| would find out the hard way they weren't safe to type
| whatever they wanted.
| chrononaut wrote:
| > I often feel like we're not in a better state these days.
|
| Reminds me of the issues with Tay:
| https://en.wikipedia.org/wiki/Tay_(bot)#Initial_release
| lijogdfljk wrote:
| Man that sounds like a ton of fun to make for an at-home chat
| bot. I used to love designing these sorts of apps for no real
| purpose lol.
| dole wrote:
| Mine suggests a personalized meal from Taco Bell.
|
| "You should get a Potato Waffle Taco Party Pack, a Grilled
| Crunchwrap Slider Quesadilla and a Smothered Cool Ranch(r)
| Doritos(r) Locos Power Bowl."
| jiri wrote:
| Yeah, thats funny. I work in the speech synthesis domain, and
| you can guess what kind of texts users are choosing most to
| generate some speech ;-)
| reaperducer wrote:
| I've never had a good experience with a chatbot. They're the
| equivalent of waiting on hold on the telephone with your bank and
| the recording asking you over and over if you know that you can
| accomplish some simple and completely unrelated task on the web
| site.
|
| It's even worse when chatbots pretend to be real people, though
| I've seen less of that lately.
|
| The Apple Card chatbot is one of the worst I've used. This is an
| actual conversation when I tried to dispute an unknown
| trasnsaction (I screenshotted it for posterity):
|
| Apple: I understand how frustrating this could be for you. I'm
| going to connect you with a specialist that will review your
| account with you and provide more specific details to resolve
| this inconvenience.
|
| Apple: Hello, I will be glad to assist you with that today. Allow
| me a few moments to review your account.
|
| Me: It's been 15 minutes. Are you still there?
|
| Apple: Welcome back. Let me know how I can assist you further.
|
| Me: What do you mean welcome back? I've been waiting for you.
|
| Apple: Sure thing. I will be here when you get back.
| jaclaz wrote:
| >They're the equivalent of waiting on hold on the telephone
| with your bank and the recording asking you over and over if
| you know that you can accomplish some simple and completely
| unrelated task on the web site.
|
| Glad to know I am not the only one hating that.
| Jorengarenar wrote:
| GPT-3: Hello, who is the President of Russia? GPT-3:
| Are you sure you want to know?
|
| I mean, maybe I don't?
| porknubbins wrote:
| Its interesting that it is so easy to get confused between a
| system that very deftly manipulates language without reference to
| an underlying reality and a (hypothetical) one that does
| understand the real world. Its akin to the problem of recognizing
| natural human BS as well and points out how our reality is
| increasingly mediated through language or other abstractions and
| how rarely we touch the real world.
| bryan0 wrote:
| There seems to be this common perception on HN that chatbots are
| good enough to pass the Turing Test thereby making such a test
| irrelevant. I'm not sure why this idea is so pervasive.
| coldcode wrote:
| Someone should use HN comments to make a chatbot.
|
| That would at least be fun.
| jjkaczor wrote:
| Too late.
|
| (Ducks - and runs for cover...)
| kibwen wrote:
| Here's an entire subreddit populated exclusively by GPT-2 bots,
| where each bot is trained on the output of a different single
| subreddit: https://www.reddit.com/r/SubSimulatorGPT2/
| TedShiller wrote:
| It's called artificial intelligence for a reason. Because it's
| not intelligence.
| visarga wrote:
| > It's called artificial intelligence for a reason. Because
| it's not _human_ intelligence.
|
| FTFY
|
| It's slower at learning basics, slower at learning new tasks,
| makes silly mistakes often, but it's growing at a speed much
| faster than biological evolution. And when there is extensive
| data it surpasses humans.
| aaron695 wrote:
| Crontab wrote:
| I know this will probably sound dumb but I've always wanted my
| own personal chatbot; one that could remember facts from previous
| conversations. I just like the idea of having my own, personal,
| electronic confidante.
| tibbar wrote:
| It's reasonable to try GPT3 out with all default settings as the
| author seems to do and provide an assessment, but it's not clear
| the author is aware of the extent to which you can configure the
| model and how the quality and variety of results will vary as a
| result. For instance, the author doesn't go into detail on the
| prompts he's using (maybe there are none other than his
| questions.) This is a little misleading because GPT3 benefits a
| lot from having good prompts to warm it up, as many
| investigations have illustrated. Plus if you want GPT3 to be good
| at a specific task (for example, providing safety recommendations
| or talking about presidents) you can fine-tune it. Also the
| amount of randomness/lack of repetition in GPT3's responses is
| completely configurable via the temperature parameter.
|
| Playing with GPT3 is incredibly interesting and I think it
| deserves more exploration than this article provides.
| drakonka wrote:
| I was obsessed with chat bots as a teenager and used to make them
| on a website called The Personality Forge. It was all hard coded
| responses with some very minor scripting involved to do things
| like fill in the speaker's name, or skew the bot's emotions in
| relation to the speaker, and have them choose different words
| based on their emotional state.
|
| I loved reading through my bot's transcripts. They were all
| recorded, and sometimes people stumbled across him and didn't
| even realize he was a bot. This happened extremely rarely...most
| of the time, his responses were perfect examples of dumbness as
| shown in this article. He would have flashes of greatness in an
| ocean of bot stupidity.
|
| Years later, I was excited to notice that a single line from my
| one of my bot's Chatterbox Challenge transcripts was included in
| a book[1] (which was seemingly a collection of papers). He was
| mentioned in a paper called "Chatterbox Challenge as a Test-Bed
| for Synthetic Emotions", a tiny mark left on the world by my
| little bot. He may be dumb, but I was still proud. I even thought
| about buying a copy of the book, but it cost $200 and I decided I
| wasn't that committed.
|
| [1] "Creating Synthetic Emotions through Technological and
| Robotic Advancements"
| jkonline wrote:
| Wait, I still don't know:
|
| "Is it safe to walk downstairs backwards if I close my eyes?"
|
| Granted, I'm more biased here than most, I suppose. I emergently
| received 10 screws and 2 plates to repair my broken ankle, after
| falling down my home stairs last year. I wasn't walking
| backwards, nor were my eyes closed.
| readams wrote:
| Is it worth noting here that GPT-3 isn't a chat bot? It's
| intended to complete writing prompts.
| beastcoast wrote:
| Can someone design a chat system that actually remembers
| conversations? I just had this issue with Apple support. If you
| don't reply immediately you get a new session with a new
| representative and the new representative doesn't have any of the
| information from the previous session. Extremely frustrating to
| have to keep sending the same information again and again. It
| took a call to finally sort it out.
| Figuringitout wrote:
| Modern CCaSS vendors will index this conversation history.
| There is a differnece between async web messaging and chat
| itself.
| nyfresh wrote:
| The expectation seems a little harsh for the setup. GPT just
| generates acceptable text. You still need to model and verify
| object relationships, use facts from a knowledge base and
| discriminate the generated responses at the very minimum.
|
| Any GPT model is just one component inside of a chatbot, not a
| chatbot itself.
| dexwiz wrote:
| 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 directed to chatbots are because they
| are really intrusive. You scroll through a page, and 15 seconds
| in your focus is disrupted as a fake chat window opens up. This
| is the digital equivalent to the annoying sales rep who asks you
| if you need help when you are clearly just browsing. The
| difference is a good sales rep has the intelligence to turn that
| conversation into a sale. A chatbot usually has to hand off the
| conversation to a real person to do this. So it has all of the
| annoyance without the benefit of a potential conversion.
|
| Chat bots as frontends for help desks make sense, but they are
| poor sales people. If companies learned the difference, I bet
| their perceived usefulness would change.
| cptskippy wrote:
| > a good sales rep has the intelligence to turn that
| conversation into a sale.
|
| A good sales rep knows when to walk away.
| aidenn0 wrote:
| Just please give me a DTMF tree as a fallback for voice
| recognition. I was trying to make a change to a rental-car
| reservation from a noisy airport, and I spent 15 minutes trying
| to get through the voice-recognition chatbot...
| tetha wrote:
| 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 human will look at, or until it can provide an FAQ entry
| fitting your problem. From a customers perspective, avoiding 5
| - 10% support calls makes monetary sense, and from a (test-)
| user perspective, it's suprisingly decent if the knowledge base
| behind it is solid. And yes, "Fritzbox doesn't internet
| properly anymore" actually had helpful results.
| Teandw wrote:
| Is the 5-10% savings on agents handling phone calls worth it
| when reputation damage is taken into consideration?
| tetha wrote:
| Most of our customers use these kinds of chat bots as an
| addition to their portfolio of support channels a user can
| use. If you don't like it, use another channel you prefer.
| a-dub wrote:
| yes, you can trip them up quite easily... and yes, they're not
| "thinking."
|
| but, i have been really impressed by how far the google assistant
| has come. it's still a dumb machine, but a dumb machine that can
| find precise and factual answers for specific questions via a
| voice interface. it's, dare i say, useful!
| Traster wrote:
| This is essentially why I think we're not going to get self-
| driving. A few years ago we produced something that could do a
| good job of pretending to drive under a _tiny_ number of
| circumstances, and people went "OMG it can drive!" and assumed
| that we just have a few corner cases before the chat bot can have
| a conversation about anything. The truth is that often these very
| limited solutions are just that - limited, they aren't just a
| linear step on the way to something amazing. Tesla will release
| self-driving on the same day their cars can hold a conversation
| with you.
| jimmaswell wrote:
| I've found them useful for locating a page or process that I
| couldn't find in a poorly designed website's labyrinth.
| DonHopkins wrote:
| Doctor, written decades ago in Emacs Lisp, did a pretty good job
| of psychoanalyzing RMS's problems.
|
| http://www.art.net/studios/hackers/hopkins/Don/text/rms-vs-d...
| _jal wrote:
| Chatbots are simply another mechanism for pushing costs on to
| your customers. When something I pay for forces me to waste my
| time, I tend to switch to a vendor who treat customers like
| people.
|
| Because shoving a shitty robot that saves you some money at the
| cost of annoying people who are paying you is disrespectful, and
| I've learned to avoid people who act that way.
|
| As but one example, I finally got annoyed enough with Capital
| One's aggressively annoying automated bullshit to switch that
| card to a credit union that's actually made of humans. I don't
| really use the much lower interest rate, but that was a nice
| bonus.
| r0m4n0 wrote:
| There is a medium though, that will ultimately save you
| money/time. If every company had to spend time answering every
| small question with a full time employee, your services would
| be a lot more expensive, hold times might be longer too. Not
| all customers are like you. My grandpa calls in to his ISP when
| his internet doesn't work when it can be solved by simply
| unplugging his equipment (and I'd wager this is true for the
| majority of the population). I don't think there is anything
| wrong with adding a simple interface layer to ensure the
| problem the needs to be addressed requires a real person. Not
| defending all practices out there right now (because I too have
| been annoyed, NY Times *cough) but some well placed shitty
| robots might be in your best interest as a customer.
| SavantIdiot wrote:
| Using Feynman to throw shade at Minsky. Nice.
|
| I read "Age of Intelligent Machines" by Kurzweil in 1990 and so
| far he's the only one that thinks human-like AI won't be until
| the 2100's, but he also has a more holistic view of intelligence
| (e.g., comparing evolution as an intelligent process with an IQ
| <1 to a dragonfly).
|
| I'm still waiting for detection network (Yolo/MNSSN) that can
| actually work on non-canonical images.
| serverlessmom wrote:
| Truthfully whenever I have been forced to interact with a chat
| bot designed by a business I have come to the conclusion that it
| is not there to help me, it is in fact there to frustrate me
| beyond belief and push me into giving up on seeking whatever help
| it is that I need. Chat bots while sometimes amusing often turn
| into a huge time sink as I try to interpret how it was programmed
| and how I can issue the correct commands to get me through to an
| actual person.
| dmkirwan wrote:
| While the tech is constantly advancing, I have yet to use one in
| anger that fully solved my problem outside of giving me
| information that's already easy to find.
|
| I think the only place it makes sense is in very very specific
| use-cases. Think about, say, a dental clinic. I would guess that
| if you put a human on chat support for a year in that setting,
| you'd see common themes emerging in customer problems. Maybe you
| develop a good library of canned responses and you find they work
| for 70 - 80% of queries, great. Then you could probably build a
| good chat bot to handle questions and handle
| cancelling/rescheduling appointments.
| ChefboyOG wrote:
| I think this gets at what the actual value prop (not the
| marketed one) of chatbots really is: scale.
|
| There will not, in the foreseeable future, be a
| model/ensemble/pipeline capable of conversing at the level of a
| human representative. Thinking of them as "humans, but cheaper"
| is destined to fail.
|
| There are, however, use-cases where communicating with a huge
| group of individuals on a one-on-one level is useful. For
| example, years ago a company called Mainstay (then AdmitHub)
| built a chatbot for Georgia State designed to reduce "summer
| melt," a phenomenon in which intending freshmen drop off
| between graduating high school and enrolling in classes. For
| this use case, getting human-level conversation wasn't as
| critical as effective performance on tasks like question
| answering. Their bot, Pounce, was credited with a ~20% decrease
| in summer melt. They have a proper study here:
| https://mainstay.com/case-study/how-georgia-state-university...
|
| This is an example, in my opinion, of the sweet-spot where
| intelligent, individualized, but not-near-human-level
| communication is needed, at a scale that goes beyond what you
| could reasonably do manually without an enormous dedicated
| staff.
|
| Now, I don't know how numerous those opportunities are, or if
| they come anywhere close to the level of hype and funding
| chatbot companies have received. I just think that in a vacuum,
| there is a set of problems where they have value.
| hereforphone wrote:
| You know what they call a quarter pounder in France?
| [deleted]
| andrewla wrote:
| The ending is the relevant bit:
|
| > As I have said many times, the real danger today is not that
| computers are smarter than us, but that we think computers are
| smarter than us and consequently trust them to make important
| decisions they should not be trusted to make.
| scotty79 wrote:
| 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.
| jug wrote:
| GPT3 chatbots are what the majority of the article is about.
| scotty79 wrote:
| Yeah, but it's different to read about it and converse with
| it yourself. It feels like a human, just the one that doesn't
| care about you or the truth.
|
| There was a research about plugging such models into the fact
| database and it resulted in better answers with smaller
| model.
| qaq wrote:
| well wait for Web3 chat bots
| staindk wrote:
| "Please pay 0.1 eth for an NFT of your chat transcript"
| Sohcahtoa82 wrote:
| I can't tell if this is satire. Poe's Law in action here.
| rchaud wrote:
| "Thank you for contacting Ethereum's Domain Name Service. We
| are currently experiencing high call volumes. To reduce your
| wait time, please pay 0.1 ETH. Gas fees may apply"
| schleck8 wrote:
| "The Icelandic power facility our bot depends on is currently
| overloaded by mining rigs, please wait several minutes for"
| klyrs wrote:
| 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 you mean by [noun in previous
| sentence] bot> why are you calling me mean? That
| really hurts my feelings
|
| It has been a few years, and I feel like a smart bot-writer might
| be able to leverage something like GPT3 to at least include a
| little bit more of the current transcript into the prompt to at
| least superficially address this gaping flaw. Have they?
| hotpotamus wrote:
| 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 the current president". Seems like a slam dunk but it could
| not be answered. Interestingly this is a common question
| paramedics will give to people who have suffered head injuries
| to assess consciousness.
| dane-pgp wrote:
| > this is a common question paramedics will give to people
| who have suffered head injuries to assess consciousness.
|
| I can't help wondering what the assessment would be if
| someone answered "Who is the current president?" with "Watson
| Bakery".
|
| https://www.youtube.com/embed/cS1Tmz816hk
| aidenn0 wrote:
| To be fair, if I were asked the current PM of Japan the
| only name I could come up with is Abe, and that's only
| because he was PM for so very long.
| jhbadger wrote:
| >who is the current president?
|
| I wonder what happened to IBM Watson's technology that was
| good at answering trivia -- it actually won a game of
| Jeopardy! a decade ago (although of course it answered things
| with a question as per the rules). I know that they weren't
| that successful at applying it to biomedical research as they
| had hoped, but it would seem it would be better at chatbots
| than GPT-3 and other deep-learning models.
| Spooky23 wrote:
| The problems with chatbots have nothing to do with tech.
|
| You implement chatbots to bend the demand curve to higher
| cost channels. Period.
|
| If you can get 5% of the user base to wait 15 minutes by
| sending them to a chatbot tarpit, you will have eliminated
| the need for a dozen call center agents at peak times.
|
| Providing _good service_ with a chatbot is possible, but
| the work and organization required is extensive, and it's
| cheaper to throw semi-skilled humans at it!
| jazzyjackson wrote:
| I suppose it didn't work with less than 15 terabytes of RAM
| AussieWog93 wrote:
| For anyone wondering, this is not an exaggeration. Watson
| actually had 15 (or 16, depending on the source) TB of
| RAM, as well as a 2880-core processor.
| jazzyjackson wrote:
| "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
| klyrs wrote:
| Hidden in my comment is a question: has anybody even _tried_
| to included previous lines into the prompt, and does that not
| help? Asking here because there are a lot of ML nerds who
| could probably do a proof of concept in a few hours, if not a
| few lines of code, so there 's a decent chance I'll get an
| informed response.
| DrammBA wrote:
| So that's a "no" for the "but did you read the article?"
| question?
| klyrs wrote:
| That is interesting. Please go on.
| YeGoblynQueenne wrote:
| In most of the conversations with GPT-3 that you see online
| what people do is that they take the output from the first
| prompt and include it in the next prompt. That is how GPT-3
| can keep the thread of the conversation going without
| changing subject constantly. This is also why those
| conversations are relatively short, because as you can
| imagine, if you keep feeding the output to the language
| model as input, you run out of input size very quickly.
|
| So, yes, that's the done thing already.
| hotpotamus wrote:
| My guess (and I'm certainly no expert here) is that not
| only have people put a few hours or lines of code into it,
| but probably many a PHD thesis as well. It's an intensely
| researched topic which makes the article even more
| surprising to me.
| AshamedCaptain wrote:
| A lot of chatbots from 20 years ago did that. They would
| even use it as a escape route, and would just bring back
| the previous topic of conversation (from say 10 lines ago)
| when they could not figure out something to come up for the
| current prompt. It really didn't help the illusion; rather
| it was even more obvious.
| lupire wrote:
| Google Meena
|
| https://ai.googleblog.com/2020/01/towards-conversational-
| age...
| thaumasiotes wrote:
| > I also wonder if there is anything out there that can even
| "remember" the context of a conversation it's supposed to be
| having.
|
| IBM's Watson project involved an internal model of the world,
| though I have no idea if that got specialized into a local
| model of an ongoing conversation. Same type of thing though.
|
| Having a context of this type available is actually necessary
| if you want to synthesize sentences in a language with
| definiteness-marking, such as English, because definiteness
| is marked according to whether the noun in question is or
| isn't already part of the context.
| Sohcahtoa82 wrote:
| > Particularly interesting is the question from the article,
| "who is the current president". Seems like a slam dunk but it
| could not be answered. Interestingly this is a common
| question paramedics will give to people who have suffered
| head injuries to assess consciousness.
|
| Not sure you'd still be able to use that question considered
| the insane QAnon followers that would answer "Trump".
|
| Though I suppose even that answer would still at least prove
| some level of consciousness.
| imglorp wrote:
| The self driving people talk about time domain occlusions,
| which seems closely related to conversation context.
|
| Say you're driving along and you see a pedestrian about to
| cross but something blocks your view for a moment. Your mental
| model will remember that person, continue to speculate on their
| motion and intention, consider if their vector might intersect
| yours, and also know when it's okay to flush them from
| attention.
| Phelinofist wrote:
| 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.
| throwaway675309 wrote:
| Eliza was modeled after Rogerian styled psychology, it uses an
| almost Socratic method to illicit and draw out responses from
| users.
| Sharlin wrote:
| The GPT2 version of the _AI Dungeon_ [1] could keep track of
| context for maybe couple of lines at a time. I 've heard the
| GPT3 version is substantially better.
|
| The problem is, of course, that these "AI" chatbots on
| websites, marketing buzzwords notwithstanding, have very little
| to do with state-of-the-art machine learning, and are indeed
| unlikely to be any more sophisticated than the original ELIZA
| for the most part.
|
| [1] https://play.aidungeon.io/
| 300bps wrote:
| Thanks for the link to that! I tried it out just now and I
| have to say that I am not impressed.
|
| _What will you do?_
|
| _You get longsword from the ground._
|
| _You get your longsword from the ground. You hold it in your
| hands and examine it for a moment. It 's a very sturdy
| weapon._
|
| _The knight then grabs his longsword and bows._
|
| Huh? Why did it grab the bow as well?
|
| _You inventory._ _You have a crossbow._
|
| Huh? I thought I just grabbed my longsword and bows.
|
| _What will you do?_ _You don 't have enough experience to
| know what a good shot is._ _You get longsword and bow._ _You
| grab the bow and the longsword. You examine the crossbow. It
| 's a bolt-action weapon._
|
| Huh? I said to get the longsword and bow since it said it
| wasn't in my inventory and it added all this extra stuff.
|
| _You inventory._ _You have a crossbow, a short sword, a
| longsword, a lantern, a flint and steel, and a quiver of
| bolts._ _What will you do?_
|
| _You load the crossbow._
|
| Huh? I just said Inventory and now I have all this extra
| stuff it never mentioned before and then unsolicitedly told
| me I loaded the crossbow.
|
| I have to be doing something wrong. Zork from 1980 was better
| than this.
| mithr wrote:
| I think things started to go wrong here
|
| > The knight then grabs his longsword and bows.
|
| "bow" here probably refers to "a bending of the head or
| body in respect, submission, assent, or salutation", rather
| than to the weapon. The knight grabbed his longsword and
| bowed to you. Your confusion then confused the game.
|
| This does expose an interesting common "failure mode" for
| these types of bots: they assume that all conversations are
| rational, and are conducted in good faith (as in, no one
| misunderstands or is actively trying to confuse them).
| Janelle Shane likes to test AIs that attempt to describe
| the content of images by asking "how many giraffes are in
| the picture?", and since most of these have been trained to
| answer what _is_ in a picture rather than what 's _not_ in
| a picture, they tend to assume that there _must be_ some
| number of giraffes, and provide answers like "there are
| 1.5 giraffes".
| 300bps wrote:
| Not a bad theory but the very first thing I did was enter
| "look" and it did say there was a longsword on the ground
| and a bow on the table.
|
| Here is the entire unedited transcript:
|
| "Good luck, my friend!" the man says.
|
| You inventory.
|
| You have a short sword, a longsword, a shield, and a
| crossbow with bolts.
|
| You look.
|
| You look around and see a longsword lying on the ground
| and a bow on a table.
|
| A large dragon looms in the background, breathing fire.
|
| What will you do?
|
| You get longsword from the ground.
|
| You get your longsword from the ground. You hold it in
| your hands and examine it for a moment. It's a very
| sturdy weapon.
|
| The knight then grabs his longsword and bows.
|
| You inventory.
|
| You have a crossbow.
|
| What will you do?
|
| You don't have enough experience to know what a good shot
| is.
|
| You get longsword and bow.
|
| You grab the bow and the longsword. You examine the
| crossbow. It's a bolt-action weapon.
|
| You inventory.
|
| You have a crossbow, a short sword, a longsword, a
| lantern, a flint and steel, and a quiver of bolts.
|
| What will you do?
|
| You load the crossbow.
|
| You shoot dragon with crossbow.
|
| You grab the crossbow and aim at the dragon's eye.
|
| The knight releases a string and a bolt flies into the
| dragon's eye.
|
| The dragon roars loudly and swipes a massive claw at the
| knight.
|
| You health.
|
| You are hit in the chest and knocked back. The knight
| rolls to the side and looks at you. The knight is
| laughing.
|
| The dragon swipes a claw at you and you are sent spinning
| to the ground.
|
| You stab dragon with longsword.
|
| You stab at the dragon's leg and the sword goes right
| through.
|
| The dragon roars and swipes a claw at you.
|
| You roll to the side and dodge the claw.
| harpersealtako wrote:
| I've been using AIDungeon (and its successors like
| NovelAI which are more for advanced users) for years now
| and have been involved in a lot of the community around
| it. You are definitely using it wrong, but you are
| forgiven because AI Dungeon is terribly falsely
| advertised.
|
| Your main mistake is not writing proper sentences. AI
| Dungeon is not a Zork simulation where you type truncated
| commands like "get torch" and receive a response from the
| computer. It is more like a Choose Your Own Adventure
| novel generator.
|
| You need to write proper sentences, so instead of "You
| inventory", try "You double check what items you have in
| your rucksack." Instead of "You get longsword and bow",
| you should be typing "You pick up the longsword and the
| bow." Instead of "You health", you...just don't do that.
| Maybe try something like "You look down at your body and
| survey your wounds." If you're really feeling confident,
| try switching from "Do" mode to "Story" mode, and just
| start writing a fantasy novel and see what it generates
| with its next output.
|
| For reference, this is a snippet of an old story of mine
| I saved:
|
| ----
|
| As I approached the kobold stealthily, it looked up with
| its beady, reptilian eyes. It could not see me yet, but I
| knew it was only a matter of time before it sensed my
| presence.
|
| I decided to act first. "Let's go!" I shouted to my
| companions, before rushing towards the small monster with
| my dagger drawn.
|
| The kobold yelped in surprise before pulling back its bow
| and firing an arrow at me. I moved to dodge it and barely
| managed to avoid it. Now in melee range, I raised my
| dagger into the air before plunging it towards the
| kobold's torso.
|
| It struck the monster's heart, and blood spurt out of the
| wound as it struggled, before going still.
|
| ---
|
| Nearly every sentence there was partially AI-generated in
| AI Dungeon, retried a few times, edited, and truncated to
| fit the story. This is how most people in the community
| actually use this sort of software. It's more like having
| a buddy suggesting the next sentence in your personal
| story than a virtual dungeon master. Those who expect it
| to be the latter generally don't understand it, while
| those who see it as the former immediately understand
| what the hype is about and get really passionate about
| it.
|
| AI dungeon might advertise itself as a game, but in
| practice it's used as a more general storytelling aide.
| And it should be noted that it has been rendered obsolete
| by competitors made by disgruntled fans like NovelAI for
| a while now (which is a whole other story).
| YeGoblynQueenne wrote:
| You mobbed a little cobold and killed it and now you feel
| all big and proud of yourself? Well done >:(
| harpersealtako wrote:
| Actually that story was really funny, the AI constantly
| kept having my character have this irrational hatred of
| kobolds, like "they're pests to be exterminated" even
| though I included descriptions of their vibrant art and
| tapestries and language and culture. Which was funny
| because it was a story about traveling with an
| intelligent slime buddy who all the humans thought was a
| "monster to be exterminated". I was ultimately planning
| on having us escape to the monster kingdom where we
| learned that not all monsters are evil, and find a bunch
| of friendly kobolds, but I never got that far before the
| site went to shit.
| cableshaft wrote:
| ...so you're saying NovelAI is better for story
| generation? Hot damn. I was having a good time with AI
| Dungeon (to the point where I was considering writing
| short stories using it as a guide), I might have to give
| that a try too.
|
| Here's a snippet from my AI dungeon story recently. Mine
| never seems to get into actual dungeon crawling. The only
| parts that aren't A.I. generated in this section are the
| lines that have --me-- before them:
|
| Veronica sits down on a stone bench. She says "Well, I
| guess we should talk."
|
| Jesus sits down next to her and asks her, "What is the
| worst thing you've ever done in your life?"
|
| Veronica says "I killed my first husband."
|
| Jesus asks "Why did you do that?"
|
| Veronica says "He was going to take everything from me."
|
| Jesus says "How so?"
|
| Veronica says "He knew where I hid all of my money, and
| he was going to take it. I would have been broke
| forever."
|
| Jesus says "That's sad."
|
| --me--: You say "Wait, you killed your first husband? I'm
| your new husband! Are you going to kill me too?"
|
| Veronica looks away from Jesus. "No. I didn't mean to
| kill him. He was just... so mean to me. I just wanted to
| stop him. I didn't..." Veronica finishes by saying "I
| didn't mean to kill him."
|
| Jesus says "Alright, I forgive you."
|
| --me--: Veronica says "Does that mean I get to go to
| heaven now?"
|
| Jesus says "I'll let you make that decision as soon as we
| finish our meal. It will have both heaven and hell as
| options, and that's all you'll ever get out of me."
|
| Veronica smiles.
| harpersealtako wrote:
| NovelAI is literally built by disgruntled AI Dungeon fans
| after the censorship scandal who wanted a better, more
| privacy-focused AI Dungeon for story generation. If you
| think AI dungeon has some cool features, you ain't seen
| nothing yet. There's a prompt tuning system called
| "modules" which basically primes the AI to write in a
| certain style, like a certain author or genre, etc (there
| are dozens of default modules, plus an included API to
| train your own, and you can share them and import other
| people's modules freely. Want a module trained on all of
| Harry Potter, or trained specifically on a particular
| genre of erotica? Someone's probably already made one).
| That's only one of the cool features it has, there are
| plenty others.
|
| General upsides: There's a billion different settings and
| dials and output customization. The context limit is 2048
| tokens is almost 3 times larger than AI Dungeon's.
| Everything is extremely transparent as far as inputs and
| outputs go, and the UI is really clean and functional,
| it's more like a word processor than anything. There's no
| crappy energy system like AI Dungeon either. Everything
| is run on private servers and encrypted so the devs
| couldn't snoop on your stories even if they wanted to
| (which was the main reason it was created, after it came
| out the AI Dungeon devs were reading and censoring
| private stories) and there's no risk of Google or
| Microsoft butting in and forcing them to change their
| business model like AI Dungeon. It's even got a legacy
| DO/SAY/STORY choose-your-own-adventure mode/module for
| people nostalgic about the AI Dungeon aesthetic. The base
| AI is finetuned on a large, curated collection of novels,
| rather than on a bunch of garbage CYOA stories written by
| 10-year-olds like AI Dungeon.
|
| General downsides: It's paid subscription only, though I
| think there's actually a free trial nowadays. It uses
| eleutherAI's GPT-J-6B, which is about 1/40th the size of
| GPT-3's largest model which is 275B. It definitely
| punches above its weight class though and subjectively
| has comparable or higher output quality to AI Dungeon's
| "Griffin" which used a smaller GPT-3. And they're coming
| out with a 20B model too in like...a week or two.
| CRConrad wrote:
| Yes -- "the knight then grabS his longsword and bowS.".
| That 's' at the end there indicates present tense of the
| verb "to grab" and "to bow", just like in "roars and
| swipes". (I guess for knights it's just good manners to
| thank by bowing when they're gifted a sword.) It's not a
| plural marker of a noun, because there was only one bow
| on the ground.
| cableshaft wrote:
| Sounds like you're trying to play it like Zork too.
|
| It's better to treat it more like collaborative story
| telling. It will let you "do" whatever you want. You don't
| have to 'check inventory'. If you want to shoot someone
| with a bow, you say "I shoot the knight with the bow". And
| you've done it.
|
| It never contradicts you and says "You can't do that, you
| don't have a bow." It just rolls with whatever you've just
| said.
|
| And it gets things wrong, sure. It sometimes has characters
| say things that I'm like "No wait, I was the one that said
| that, why are you acting like you said it?" Or contradicts
| what just happened. Or has you move into places that don't
| make logical sense (like exiting a detached garage at your
| house to enter a small room, etc), but correct it and go
| on.
|
| But one thing it lets you do is either have it retry, or
| you can just click and edit their response to something you
| would rather it be.
|
| "But why don't I just write a story on my own if I have to
| edit it to be what I want?"
|
| Because it comes up with shit that I would never think of
| on my own. I fought an evil Super-Man in the bottom of the
| sea, and he chased me into a classroom, and saw a dog
| behind the desk, and got distracted from attacking me and
| wanted to pet the dog.
|
| Even better, later we won a trip to the Louvre. The Louvre
| welcomed us as if it were a towering person, put on a fancy
| dress, and when we entered, Mona Lisa came back from the
| dead to give autographs next to its painting, the third
| floor had Poussin paintings running around as if in a horse
| race, and another floor let you walk into a painting, where
| we entered one with Jesus serving a man and a woman dinner,
| and Jesus offered us each two plates, one with a pea and
| one with a feast, and the signs heaven and hell under them,
| and whatever one we ate was the one we went to.
|
| Some of that was me guiding the story a little, but I
| wouldn't have thought to direct the story that way if not
| for some of the unexpected things generated by the A.I.
|
| I've played Zork. Zork has puzzles to solve, something AI
| Dungeon can't handle, but AI Dungeon has a lot more
| freedom.
| [deleted]
| Traubenfuchs wrote:
| aidungeon is a bad joke, I do not understand why anyone is
| wasting their time with this?
|
| You go on an adventure.
|
| You hitch a ride on a passing ship and get taken to some
| far away planet. You get to explore and have fun.
|
| But the planet is a dead world with nothing to eat except
| for some tree sap.
|
| You pet the deer.
|
| You pet the deer and it gives you a venereal disease.
|
| Then the planet falls into a black hole.
|
| You survive by eating the deer and planet.
|
| It just said, the planet is a dead world. Why is there a
| deer? Almost zero short term memory. No logic.
| harpersealtako wrote:
| AI Dungeon (and its successors like novelai [1] and holoAI
| [2] following its infamous censorship purges and mutinies) is
| basically designed entirely around that problem and has a lot
| of clever solutions that let writers keep relevant context in
| memory in a story that is longer than the model's maximum
| input length.
|
| * "Memory", which is a customizable block of text that is
| repeated at the top of each API input. If your story revolves
| around your character being a vampire who melts in the
| sunlight, you can include something like "you are a vampire
| who will die if you go out in the sunlight" in the memory,
| and even 1000 characters back a paragraph of context can
| prime the AI accordingly.
|
| * "Author's Note", which is a customizable short block of
| text that is inserted invisibly a few lines before your
| current place in the story when it's sent to the API. A note
| such as "[A/N: The following section includes depictions of
| graphic violence]" or "The following section is written in
| Shakespearean old English", as obvious and blunt as it might
| seem, actually works surprisingly well for nudging the AI
| towards a certain style or content.
|
| * "World Info", which is a customizable dictionary of short
| text blocks that are conditionally added to the top of the
| API input like memory when a certain key appears in the
| current context. Imagine you have a story with 10 important
| characters who cycle in and out of the story. If you create
| an entry in the world info about Bob, then when you write
| that "Bob appears from behind the shrub", the blurb about Bob
| is automatically tacked on to the context so long as Bob is
| mentioned by name in the last few dozen inputs.
|
| In general, both GPT-3 and the open source alternatives by
| EleutherAI such as GPT-J-6B are able to use a context primer
| from 1000 tokens prior to affect the current tail of a story.
| It's actually kind of uncanny how good they are at it -- you
| can have a story that in the memory at the top says "goblins
| always have purple skin" and notice that the AI will mention
| it as an offhand detail much farther down in the context.
|
| [1] https://novelai.net/ [2] https://writeholo.com/
| patresh wrote:
| There is a fundamental difference between AI Dungeon-type
| chatbots and chatbots you typically encounter on websites
| e.g. for customer support.
|
| The former does not really have a goal and is unconcerned
| about responding with factual information as long as the
| conversation is coherent. It makes sense to use large
| language models that are quite good at modeling next word
| probabilities based on context.
|
| The latter however is goal-oriented (help the customer) and
| constrained by its known actions and embedded knowledge. This
| often forces the conversational flows (or at least fragments)
| to be hard-coded and machine-learning is used as a compass to
| determine which flow to trigger next.
|
| For now controlling GPT-like language models remains an
| extremely tricks exercise but if some day we can constrain
| language models to only output desirable and factual
| information with a low cost in maintaining and updating its
| embedded knowledge, we should see a significant bump in
| "intelligence" of the typical website chatbot.
| not2b wrote:
| Eliza had a little, but very limited memory, and sometimes when
| no rule would match it would say "Earlier you said <x>". There
| was some dumb heuristic about which <x>'s to save for this
| purpose.
| masswerk wrote:
| For the record, ELIZA does have a short term memory, but it is
| only used as a fallback, when other rules fail to match. (E.g.,
| in productions like, _" Earlier you said *"_ or _" What else
| comes to your mind when you think of *"_ by the famous DOCTOR
| rules set.)
|
| ELIZA/DOCTOR manages somewhat to succeed with this, because it
| pretends a setting, where there are no outside references at
| all, beyond the very limited purpose of carrying on with a
| conversation that is meant to explore internal subjects in
| ever-shifting context. (You could say, the shift in context is
| the actual progress and success of the conversation, while
| having to pick up an earlier thread actually marks a point of
| failure.) Outside of this restrictive setting, the shortcomings
| of the absence of a consistent world model become obvious very
| soon.
| framecowbird wrote:
| I'm interested in chatbots for learning foreign languages. In
| that scenario I really don't care how dumb the conversation is,
| just that it's grammatically correct.
|
| Does anybody know of such a service?
| CRConrad wrote:
| I would have said "Try the support chatbot on some big service
| provider web site that uses your target language", but that
| would presume that chatbot programmers (or programmers in
| general) can write grammatically correct prose, so... Maybe
| not.
| febin wrote:
| Most people only see the AI/ML aspects or the ability to respond
| like human. But what's adding value is the chatbot's interface.
| Working for a chatbot company that hit $1M revenue I can say the
| chatbot interface solves a good problem.
|
| There's a good chunk of people who are stressed in having to be
| comfortable with vide variety of website interfaces. For my dad
| who's over 60 years struggles with the government's interface to
| avail the pension scheme.
|
| Chatbot or conversational interfaces have a repeating pattern.
| People are used to conversational interfaces because of SMS,
| iMessage, WhatsApp, FB, etc etc. Providing an experience through
| a chatbot interface reduces the learning curve for the end-user.
| You are presenting tiny chunk of information and even collecting
| one thing at a time. It's drastically less overwhelming.
|
| It's not just for 60 years, I have friends who are around my age
| late 20s who finds it difficult to navigate through websites that
| have many offerings (Banks, Govt Services, etc)
| jakey_bakey wrote:
| But it doesn't need to be a bot - lots of companies have
| conversational interfaces that aren't robots.
|
| Edit: Or maybe they're just really good chatbots!
| 0xbadcafebee wrote:
| > within "three to eight years we will have a machine with the
| general intelligence of an average human being." Fifty-two years
| later, we're still waiting.
|
| Humanity built the atomic bomb and went to the moon. But "they"
| didn't sit around waiting for it, they decided to do it, and then
| invested enough to get it done. And the reason they decided to do
| it was war.
|
| Most major technological breakthroughs are a byproduct of war. If
| AI ever gets developed, it'll be as the next weapon of war. So
| really what we're waiting for is the next war.
| pwinnski wrote:
| 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 of the amount of math and tricks
| in the average human brain, because what we have today isn't
| anywhere close.
| version_five wrote:
| 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 points out that the technology doesn't do what the
| business people think it does just gets dismissed as not
| understanding.
| dkarl wrote:
| 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.
| semi-extrinsic wrote:
| No, but most chatbots I've seen are no better than a well-
| structured FAQ page. We've had those since the mid 90s.
| soco wrote:
| Most? I'd be surprised to see _a single one_ working
| beyond the FAQ level (a very appropriate comparison,
| thank you).
| yawaworht1978 wrote:
| Some of them are literally a form linking to the faq part
| based on user input.
|
| I think it's ok as a first step to route customer care
| cases, like "payments issue","delete account" etc, but
| nothing more granular than that.
|
| That and link rot, when procedures have been updated, but
| the faq haven't. Infuriating.
| CRConrad wrote:
| > 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.
| emteycz wrote:
| They are better in that someone actually reads the
| suggestions
| version_five wrote:
| I've often argued chatbots are much worse than an FAQ.
| With proper structure, like you say, it can be easy to
| see what is and isn't covered, and for things that are
| included, look up the answer.
|
| A chatbot is like an inefficient front end on an FAQ, you
| have to guess what they might be able to do, and guess
| what might trigger them to understand you. Best case
| scenario, you get the chatbot to provide you with a
| "help" response that's basically the FAQ.
|
| A simple list of options will always beat a
| "conversational interface" to a list of potential back-
| end actions.
|
| Incidentally, I think this gets obscured a but when
| dealing with businesses whose goal is to confuse or
| frustrate you into not taking action. If you look at
| Amazon or Uber's FAQ, they are designed to take you in
| circles and prevent you from getting any recourse or
| talking to a person. Chatbots could be helpful for this
| application
| dangero wrote:
| yes chat bot interface discoverability is terrible -- in
| fact it feels like the system you would design if the
| intended goal was to intentionally obscure the interface
| surface while still allowing access to it
|
| One logical reason for obscuring the real interface is to
| make the interface appear more robust than it actually
| is, so pure marketing, but outside of that I'm not sure
| what the value is.
|
| similar to home assistants Siri/Alexa/Google where 99% of
| the creative things you try don't work so you end up with
| just using it to set timers and play music
| melony wrote:
| That's a good thing. The market is very good at empirically
| validating research. It helps filter out the chaff and ensure
| research is useful. Better than academia wasting years on
| concepts like the "semantic web" where nobody can even agree
| on what it means. Academia is under attack from many
| political directions right now, being able to show useful
| output will help it thrive in the long run.
| manquer wrote:
| Research takes time, launching something prematurely which
| is clearly not ready for practical application will sooner
| or later fail and suck out any further funding out the
| field.
|
| The goal of academic research is to further knowledge, as
| long as knowledge is produced even if is only that an
| approach will not work then they are not wasting anything.
|
| It is not job of academic research to monetize or even do
| work that can be potentially monetized. That what corporate
| research is for.
|
| If academia focused on monetization they wouldn't need to
| teach or depend on public funding to keen afloat. That is
| simply not their goal.
|
| Most academic scholars have a teaching day job and are more
| than fullfilling a useful role in society with just that .
| anything further is gravy
| KittenInABox wrote:
| > The market is very good at empirically validating
| research. It helps filter out the chaff and ensure research
| is useful.
|
| I am very skeptical and would like to see studies that
| evidence this. Counterfactually, the market would never
| tolerate the decades of research behind MRNA vaccines and
| the researchers behind it were considered useless. The
| market has also put in mind-blowing amounts of money
| towards the ameloid hypothesis behind alzheimers to massive
| disappointment.
| netizen-936824 wrote:
| I agree with you.
|
| I don't think the market is good at validating any ideas
| or research. Salespeople will talk up their product to no
| end and over promise. The only thing the market validates
| is the ability of people to sell crap
|
| Being able to sell something doesn't necessarily mean
| that thing is good or correct in any way
| [deleted]
| nfgrep wrote:
| I can understand your reason for saying this, (useful
| things often sell well) but a market only validates that
| people are willing to pay for something, not that it is
| 'valid' empirically.
| sam0x17 wrote:
| Right. By that same token, directly selling fentanyl or
| oxy to consumers without any regulations would surely
| sell well, as does nicotine, etc., but this doesn't mean
| it's good for society.
| numpad0 wrote:
| The problem with the market is it wants consistent, short-
| term successive, quantifiable production, and that seems to
| instantly kill all progress in a field of research. They
| just go laid back watching investments burn and prints
| worse and worse nonsense.
| nobodyandproud wrote:
| > The market is very good at empirically validating
| research.
|
| The market can do this, if it's correctly incentivized to
| do so.
|
| More often than not, the incentives just aren't there or
| are compelling enough.
|
| Often it's other businesses that put up such disincentives.
| sam0x17 wrote:
| Capital is far too short-sighted to look beyond this year
| or this quarter. Many of the important groundbreaking ideas
| or projects take years, even decades to formulate. As I've
| said elsewhere, capital will just take the easiest road it
| is allowed to take, which currently is stifling innovation,
| buying competitors, maintaining monopolies, relying on
| economies of scale to shut out competitors when they can't
| be acquired, and using lobbyists to ensure regulations that
| affect the status quo never pass. In the past the big tech
| corporations maintained huge corporate labs and actually
| did groundbreaking research with 15+ year projects. Now
| everything is short term. We can't even compel capital to
| see the long term value of preventing climate change, when
| Exon was aware this was going to happen as far back as the
| 1970s in excruciating detail. No, capital will innovate
| only if there are sufficient regulations in place,
| incentives, and guardrails, that there is no other choice
| than for them other than to innovate (which they will do
| begrudgingly). Capital is by no means a vehicle for
| innovation. When was the last time you saw innovation from
| Google in the search space, their bread and butter?
| beepbooptheory wrote:
| This is a really great way to frame it, because it really
| does seem to be about time/speed. I don't think we can
| even collectively comprehend great innovations that need
| many resources and time anymore, who has even the time to
| work on it? People need to have jobs after all.
| simplestats wrote:
| I cant think of the last time I saw the word
| "corporations" used in a post that wasn't part of an
| attack on them as inferior/evil/villanous etc. Speaking
| of NLP, your post would be very easy to classify
| sentiment of using a simple keyword approach.
|
| Anyway, I've worked both in academia and industry.
| Industry is simply more practical and better at
| technology. In tech areas, academia _desperately needs_
| industry to provide the feedback they provide. Especially
| in AI areas. You are thinking of CEO 's or salespeople or
| something, but the people that matter here are the
| engineers. And I'd place their assessment over that of
| grad students any day. If the engineers can't make it
| work, then yes there's a problem here. Doesn't always
| mean it can't work, but for most ideas it probably does.
|
| By the way industry research labs certainly still exist.
| But long-term self-funded research has to compete with
| govt funding of research. Why throw your investor money
| at a high-risk idea when Stanford, MIT, and 100 other
| R1's are throwing taxpayer money at it? Otherwise
| industry labs end up just competing for govt gants
| ultimately. Meanwhile nowadays we see academia chasing
| short-term problems that industry leads in (and trying to
| patent them too).
| systemvoltage wrote:
| Hot take: Corporations are also amazing. James Webb
| mirrors? Made by a private big corp (Ball Aerospace). So
| are all instruments of James Webb. NASA contracts out
| their work to many big fat corporations. Semiconductors
| to hearing aids, Corporations make the world tick.
| They're absolutely incredible. When people get together,
| they can build stuff like rockets and vaccines.
|
| Capitalism makes all of this happen. So the attack on
| capitalism is so deeply deluded, it's strange to see it
| in a tech crowd who know better. Hell, your salary
| probably comes from "Corporations". When you're in the
| hospital, note all the corporations doing evil things to
| save your life.
| pdimitar wrote:
| > _the people that matter here are the engineers_
|
| Where did you get this from? Not like they call the
| shots. Weird statement.
|
| > _In tech areas, academia desperately needs industry to
| provide the feedback they provide_
|
| That's true, I agree. But the tech industry is also very
| often ruled by the worst of humanity so it's a balance.
| klabb3 wrote:
| > 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...
| lotsofpulp wrote:
| I have to agree with this. I do not understand why I type
| all of my relevant information into a chatbot, and then a
| real person comes on the other end, and asks me all the
| same questions. Worse is when it is on the phone.
|
| I can only assume the intent is to discourage me, as that
| amount of ineptness is even more depressing to assume.
| repomies69 wrote:
| The chatbot saves money. Simple as that. People get served
| by chatbots, get frustrated, and majority gives up and
| doesn't bother the company with the problem.
|
| It doesn't really matter how the chatbot saves the money,
| they can just see the end results and use the money for
| bonuses instead.
| Maxion wrote:
| >People get served by chatbots, get frustrated, and
| majority gives up and doesn't bother the company with the
| problem.
|
| With customer service systems I have to disagree here.
| I've got experience working with these issues and for the
| vast majority of companies most contacts to customer
| support are for small, banal, things that current crappy
| chatbots can easily solve. The 80-20 rule works here too.
|
| Bad companies try to do too many things with their
| chatbots, and use it as a way to make it harder for
| customers to actually get to talk to a human.
|
| Good companies use them to allow customers to solve
| common issues faster than getting a real human on the
| line.
|
| Then there's the other issue of how people want to find
| information - some people want to find it themselfes and
| do not want to talk to a person, whereas others
| specifically want to ask someone and do not want to look
| at all. For the latter group, no chat bot or fancy
| autocomplete knwoledgebase (Looking at you Zendesk) or
| similar will work. They'll always try to contact support
| as their first step, and they will get very frustrated if
| you make it impossible.
|
| If your a more software oriented company, it can be very
| benificial to have software developers (or even a team,
| if you're a larger company) devoted to helping support.
| The majority of issues customers contact support for are
| UI/UX or business process related, and if you
| systematically start to solve them you will reduce
| customer support burden and customer support related
| costs.
| ghaff wrote:
| I suspect that in a forum like this one, most of the
| people get pushed into customer support when they've
| probably exhausted online resources (though we also all
| screw up from time to time). So, most of the time, you're
| dealing with a chatbot (or for that matter an L1 CSR--
| which often isn't a lot better) when you really need a
| human with some experience and agency to make things
| better.
|
| I even had a weird thing with Apple a couple of weeks
| ago. Some edge case related to buying something. The
| chatbot and telephone tree was as frustrating as anywhere
| else but once I got to a person it was trivial to solve.
| AussieWog93 wrote:
| >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.
|
| I'd believe that. Especially as processes mature and you
| really get your QA down pat, a good chunk of support
| requests tend to come from high-maintenance "black hole"
| customers who will only consume more of your resources when
| you help them.
| 300bps wrote:
| _We want it to be true, so we squint and connect dots and it 's
| true._
|
| I've had numerous people look at the actions of software I
| wrote over the last 30 years make comments like, "Ohhhhhh it
| probably did that because it knew x". The software had no such
| functionality. Seems to be a natural thing for people to be
| overly optimistic about software's capabilities.
| freedomben wrote:
| Heh, likewise. It's amazing how often choosing sane defaults
| and falling back to defaults in the even of error is "the
| right thing" in the eyes of users.
| throwaway0a5e wrote:
| People always over-estimate the complexity of stuff they
| don't understand.
|
| If I had a nickle for every time an internet commenter
| attributed intentional design to a feature that's simply the
| designer copying established default practice...
| robotresearcher wrote:
| ELIZA (1964) is the canonical demonstration of this
| phenomenon in software. We see faces in clouds and
| intelligence in anything interactive.
|
| https://en.wikipedia.org/wiki/ELIZA
| dragonmost wrote:
| In the game speedrunning community it's impressive the number
| of time a glitch or behavior of the game is attributed to
| "the game is confused".
| beaconstudios wrote:
| That's just casual anthropomorphisation. I think most
| gamers, especially speedrunners realise that games are
| unintelligent because they encounter and exploit
| counterintuitive reactions all the time.
| TedShiller wrote:
| The reason laypeople want it to be true is because experts
| present it as being true.
| tcgv wrote:
| And marketers
| p1esk wrote:
| As far as chatbots, we went from "tricks" to "math" in just ~10
| years. Yes, still as dumb, but the underlying "technology" is
| very different. GPT-3 is a lot closer than ELIZA to how our
| brains do it.
| chubot wrote:
| It was more than 10 years ... People reacted the same way to
| SHRDLU 40+ years ago, and 20 years ago when I encountered it:
|
| https://en.wikipedia.org/wiki/SHRDLU
|
| There's definitely an illusion where we anthropomorphize very
| simple software, ascribe intention to it, etc.
| p1esk wrote:
| I'm not 100% sure, but I think in 2012 chatbots still used
| handcoded rules. So we switched from handcoded rules to
| trainable neural networks in just a few years. Models like
| GPT-3 are interesting because they are conceptually simple,
| and are able to do (previously) complicated tasks without
| any explicit training (e.g. simply by processing lots of
| text and trying to predict the next word). This is a huge
| advancement in AI field, even if many more advancements are
| needed to get to the human level.
| fault1 wrote:
| I remember chatbots in 2000 using hidden markov models
| (and sometimes even neural nets), so from that
| standpoint, they aren't exactly new.
|
| The models are just larger now.
| JamesBarney wrote:
| Never underestimate the effects of scaling on
| intelligence.
|
| Caenorhabditis elegans neurons work a lot like our
| neurons, we just have a lot more of them.
| fault1 wrote:
| I agree with you.
|
| I also believe "AI" will always be a moving target:
| https://en.wikipedia.org/wiki/AI_effect
|
| Certainly in the 1950s, most automatic control systems
| must have seemed magical, it was to Nobert Wiener, even
| if they were "just" an evolution of the steam governor.
|
| In the end, it depends on what you qualify as
| intelligence.
| pdimitar wrote:
| > _I also believe "AI" will always be a moving target:
| https://en.wikipedia.org/wiki/AI_effect_
|
| No, it absolutely is not. Everyone I spoke with in the
| 90s (and myself) still have the same requirements: be
| able to make sense of the 3D material world around you
| and interact with it without harming humans or valuable
| possessions.
|
| Maybe you spent too much time with critics that can never
| be satisfied. Sucks to be you if that's the case but
| don't think for a second that they represent most of
| humanity. Most of us want to spend less time cleaning or
| doing stuff in the kitchen, and us the programmers in
| particular would just be grateful for faster compilers
| and a bit more declarative programming that generates
| actual code.
| majormajor wrote:
| > I'm not 100% sure, but I think in 2012 chatbots still
| used handcoded rules. So we switched from handcoded rules
| to trainable neural networks in just a few years. Models
| like GPT-3 are interesting because they are conceptually
| simple, and are able to do (previously) complicated tasks
| without any explicit training (e.g. simply by processing
| lots of text and trying to predict the next word). This
| is a huge advancement in AI field, even if many more
| advancements are needed to get to the human level.
|
| This seems like a very optimistic take on the timeline.
|
| It took us 50 years to go from ELIZA to GPT-3. And it
| still is "dumb" compared to human intelligence.
|
| So how long for the next major achievements? Are we
| talking years for each, or more decades?
| adament wrote:
| I think MegaHAL is (mostly?) just a markov model, and I
| think that was not exactly new when I looked at it around
| 2002. As I recall it was easier to distinguish from a
| human than Eliza, since it had a greater probability of
| spouting nonsense, but it was still amusing and fun to
| play with.
|
| Personal anecdote: I read one of Ray Kurzweils books in
| school back then, completely misunderstood how neural
| networks worked and ended up making a markov model
| chatbot with single word states.
| mike00632 wrote:
| What if that's the case? What if me replying to you is nothing
| more than some atomically basic mechanism of statistical
| inference and randomness? Your entire perception of my
| personhood could be based on a sense of verisimilitude without
| significant reasoning to set me apart from a transcendant
| spirit.
|
| What then? Would you be less forgiving of my mistakes if you
| knew? Would you be less proud of work we collaborate on?
| pessimizer wrote:
| The "What if human faces are actually power outlets?" theory.
| Majestic121 wrote:
| I think like OP that it's mostly math and tricks, and that
| we're far from reaching it yet.
|
| But then, the conclusion is not to be less forgiving, but
| more forgiving : we're all just meat machines, we should be
| forgiving toward each other's flaw (not naive mind you, but
| forgiving), and proud of what we reach collectively with our
| lowly condition.
| pdimitar wrote:
| > _What then? Would you be less forgiving of my mistakes if
| you knew? Would you be less proud of work we collaborate on?_
|
| Needlessly philosophical on a thread about chat bots but to
| respond to your questions: I would not give a damn either
| way. If I came to you (whatever you are as an entity) then
| I'll expect coherent and intelligent answers to my questions.
| I don't care about how you produce them.
| pwinnski wrote:
| My point is the other way around. If I knew for certain that
| you and I were perfectly deterministic, it wouldn't change
| anything about how I viewed you (especially since some days
| I'm pretty sure we're all deterministically-driven), but it
| would suggest to me that our best efforts at AGI are probably
| at somewhere in the .00000000000001% range as complex as they
| need to be to even begin to approximate our human levels of
| intelligence or understanding. Or worse.
| avereveard wrote:
| > We want it to be true
|
| Founders and salesman pretend it to be true for that sweet
| sweet VC money, while underneath devs try to fake it as
| plausibly as possible.
|
| And I'll up it with a prediction: watch closely call centers,
| and as soon as you see them closing in droves, invest in ai
| startups as something begun to really move.
| crate_barre wrote:
| It's the stupid term AI that ruined everything. Our
| predecessors had enough _intelligence_ , ironically, to call
| spellcheck what it is. Today it would be AI.
| [deleted]
| pdimitar wrote:
| You didn't have to go for the jugular and do the brutal kill on
| the first hit, dude!
|
| > _We want it to be true, so we squint and connect dots and it
| 's true._
|
| That's exactly the issue. You summarized it once and for all
| and we can all go home and stop discussing it now and forever
| (until we get a general AI that is).
|
| 1. Normal people _want_ to have intelligent machines. They
| watch movies and series and imagine one day a robot will cook
| for them so they _actively look_ for intelligence, as you said.
| They buy Roombas and imagine they are going to clean 100% of
| their rooms (seen it, heard it, watched them rage when it didn
| 't happen). They buy Alexa-enabled devices and imagine
| themselves like some aristocrats barking orders at an
| intelligent home (lol). But yeah, that's what the normal people
| do. It's quite puzzling to me.
|
| 2. People who work in the area are obviously biased and I have
| argued with some of them here on HN but I view it as a doomed
| affair. They insist there's a lot of innovation going on and
| that improvements are being done all the time yet we still have
| embarrassing failures as Michele Obama classified as a male and
| various politicians classified as known criminals or black
| people in general classified as gorillas. Like OK, where are
| your precious improvements and why are they NEVER finding their
| way into the news?
|
| "It's hard to make someone understand something if their salary
| depends on them not understanding it", that's how I view the
| folks working in the DL / ML area. Sorry if that's offensive
| but just looking from the sidelines, it seems that what I say
| is true.
| visarga wrote:
| > Michele Obama classified as a male
|
| Yes, humans don't make embarrassing mistakes all the time.
| We're only making dignified mistakes.
| pdimitar wrote:
| If something is to replace humans at doing a job X then it
| has to be better than the humans at job X.
|
| Also humans instinctively expect the machines to not make
| mistakes. I haven't made them such; it's just a fact of
| life. And we have to work with the expectations of the
| bigger populace.
| visarga wrote:
| It's not necessary to be perfect, just useful.
| hdjjhhvvhga wrote:
| > 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.
|
| I'd add it says a lot about all the companies that advertise
| them in a way that has nothing to do with reality, and those
| who actually buy them. We all know the usefulness of these
| things is below zero, because they only get in the way of
| getting actual help. And yet, someone's marketing department
| convinces a decision maker at another place they should
| implement this useless widget on their website, and that it
| will reduce the cost of customer service by X%. And they
| believe them.
| Sebb767 wrote:
| Currently, the way Chatbots are, they are just some glorified
| text boxes to enter your information in, a different format
| of the search box and lastly, a way to make sure you've done
| the basic checklist. They also hardly speak your language and
| refuse to deviate from the script in any way. Which, without
| much irony, is pretty much my experience with the first level
| support at a lot of companies. So I'd say they were quite
| successful with replacing that.
| ricardo81 wrote:
| I'm not in your field, just a vanilla programmer.
|
| The "want it" resonates. Seems like the difference is in
| receiving an answer that is relatively agreeable or sensical vs
| something that's actually substantive.
|
| And to be fair when it comes to the Turing test, there's people
| that will be overly agreeable for the sake of politeness, but
| ultimately when it comes to knowledge seeking we're after
| something more substantive.
| Krasnol wrote:
| I still have an IRC chat bot (eggdrop module). It sounds more
| interesting than some of the bots I see today and which are
| supposed to be the result of intense ML engineering.
|
| I guess the tricks did not evolve much.
| kingkawn wrote:
| That interpretation of communication is how we develop and
| craft the personalities of children. There is nothing about our
| reaction to the pre-conscious language these bots are
| displaying that doesn't fall in line with our own normal
| development patterns. And in the long run the same desire will
| lead us to develop bots that are capable of thinking.
| tomrod wrote:
| > There is nothing about our reaction to the pre-conscious
| language these bots are displaying that doesn't fall in line
| with our own normal development patterns
|
| Well... yes and no. Deployed models typically learn in a
| defined pattern, if at all. Various forms of data freshness,
| etc. to develop. But the chatbots don't have good history
| recall, typically, and know that what you mentioned 50
| messages ago is relevant to message one prior and not
| current. Things like that. We don't program pareidolia very
| well, which is typically seen as a negative, but its a
| feature for finding useful patterns (not just lowest error
| patterns).
|
| [0] https://en.wikipedia.org/wiki/Pareidolia
| kingkawn wrote:
| You misunderstood what I was saying. I know the chatbot
| itself is not structured as we are. I'm saying that our
| reactions to them are the standard tools of mind-building
| that we apply to our own kids (and pets).
| pwinnski wrote:
| If I understand you, you're saying that we see patterns
| of intelligence or understanding in ML models in the same
| way we see patterns of intelligence or understanding in
| children or animals?
|
| If so, I agree. I think that's our big flaw, in fact,
| because we instinctually apply patterns from birth, even
| when those patterns shouldn't be applied. So we see faces
| in the moon or on mars that aren't there. We see shapes
| moving in the dark that don't exist. And we seem to
| believe that ML models will develop over time as children
| or animals do, based on nothing more than our perceptions
| of similarity, our instinct to apply patterns even when
| we shouldn't.
|
| Unlike a baby human, that ML model isn't going to develop
| increased complexity of thought over time. It's already
| maxed out. New models might up the complexity slightly,
| but that baby is going to vastly surpass any existing
| model in weeks or days.
| parkingrift wrote:
| These bots seem equivalent to an adult with amnesia after
| every spoken sentence. Absolute understanding of the
| language, and some impressive display of recalling facts, but
| without any understanding of the environment or context of
| the conversation.
|
| This is polar opposite to any experience I've had with
| children. Children are aware of their environment and have
| complex thoughts, but sometimes they are unable to convey
| those thoughts with words. Children seem to remember
| conversations, and if I were to say "Go get me a red lego"
| and then subsequently say "now a green one" there is no
| ambiguity or confusion.
|
| To me as these bots have "advanced" it has only highlighted
| how absurdly far we are from anything even approaching actual
| intelligence, even the intelligence of a toddler. The
| contextual awareness I have seen in bots is not much more
| than a cheap trick that is trivially fooled in scenarios that
| would not fool a child.
| perryizgr8 wrote:
| When you talk to children who haven't developed the skill
| of talking completely, you still get the sense that there's
| a lot going on inside that they're unable to express.
| Sometimes they will show it to you with their actions. I
| wonder if chat bots are also struggling with the language,
| but have an internal story that's playing out, desperate to
| be understood. But they can't, because the only interface
| they have is a stream of text.
| immibis wrote:
| I remember reading a paper showing that GPT-x bots are
| more likely to get simple tasks correct (e.g. multi-digit
| math) if you ask them about each step. This suggests the
| text stream really is all there is. Well, there is some
| internal state, but not a lot that isn't text.
|
| (For example, if you ask it to add 123 and 457, it'll
| probably get it wrong. But if you ask it what to do
| first, it'll say add 3 and 7. If you ask it what that is,
| it'll say 0 carry 1. And so on)
| katmannthree wrote:
| > how absurdly far we are from anything even approaching
| actual intelligence, even the intelligence of a toddler
|
| I respectfully disagree, IMO we're past that point although
| not by much. You might enjoy conversing with one of the two
| current GPT-3 davinci models. They do an excellent job of
| understanding the context of many discussions, right up to
| the ~8000 char token limit. If you want to have a nice
| existential discussion it does a remarkably good job of
| providing internally consistent results.
|
| After using it for a while you'll notice that there are
| some categories of conversation where it does exactly what
| simpler chatbots do and regurgitates what you sent it with
| a few words tacked on for negation or whatever, but there
| are many subjects where it is clearly not doing that and is
| in fact synthesizing coherent responses.
|
| Depending on how you initiate the conversation it may
| identify itself as a bot attempting to pass a Turing test
| and (very correctly) avoid comments on "what it's like in
| its home" or what its favorite foods are, instead replying
| that it is a bot and does not eat food, etc. The replies I
| got here were not exactly substantial but the level of
| consistency in replies of what it is/has/does is
| unparalleled.
|
| If you start the conversation with other prompts
| (essentially signaling at the beginning that you're asking
| it to participate in a human-human conversation) it will
| synthesize a persona on the fly. In one of those sessions
| it ended up telling me where it went to church, even giving
| me the church's street address when asked. Interestingly
| there is in fact a church there, but it's a roman catholic
| church and not lutheran as GPT-3 was claiming. It provided
| a (completely inaccurate) description of the church, what
| it likes about going there, why it chose that religion over
| others (something about preferring the lutheran bible to
| other options due to the purity of the translation, it has
| clearly consumed the relevant wikipedia entry). If you ask
| it basic theological questions it's able to provide self-
| consistent and coherent answers which do not appear to map
| back to phrases or sentences indexed by Google. Whether or
| not its opinions on those matters have utility is an
| entirely different thing altogether, but discussing
| theology with bots is fascinating because you can assess
| how well they've synthesized that already-a-level-away-
| from-reality content compared to humans. GPT-3 at least in
| my experience is about as good (or not, perhaps that's
| better phrased as a negation) at defending what it believes
| as many humans are.
|
| The bigger issue with its church is that it's 400+ miles
| away from where GPT-3 said it lived. When asked how long it
| takes to drive there every sunday, it answered 2 hours
| (should about 8 according to google maps). How can it do
| that you may wonder? "I'm a very good driver." The next
| question is obviously what car they drive and how fast it
| can go (a Fiesta, with a max speed of 120 mph). Does it
| know how fast they would need to drive to make that trip in
| two hours? Yes, about 200 MPH (which is more or less
| correct, a little on the low side but it's fine).
|
| GPT-3's biggest weakness, as TFA mentions, is an almost
| complete inability to do any kind of temporospatial
| reasoning. It does far better on other kinds reasoning that
| are better represented in the training data. That's not
| exactly surprising given how it works and how it was
| trained, asking GPT-3 to synthesize you information on
| physical interactions IRL or the passage of time during a
| chat is a bit like asking someone blind from birth to
| describe the beauty of a sunset over the ocean based on
| what they've heard in audiobooks. Are the 175B parameter
| GPT-3 models a true AGI? No, of course not. They are
| _something_ , though, something that feels fundamentally
| different in interactions from all of the simpler models
| I've used. It still can't pass a Turing test, but it also
| didn't really fail.
| not2b wrote:
| No, they still lack the common sense of a toddler,
| because they don't know anything about the world; they
| only know (in great detail) about the structure of their
| training data.
| immibis wrote:
| They draw on massive piles of the output of human common
| sense. View it as a very sophisticated auto-complete
| module that's fun to play around with.
| katmannthree wrote:
| That's more or less what I was trying to say. The
| expensive GPT-3 models do a remarkably good job of
| synthesizing structure which is readily parsed from the
| training data, and a very poor job with structure
| (particularly temporospatial structure) which is not.
|
| A toddler can reason about time and space far better than
| GPT-3 (which is not a high bar, I'm pretty sure my parrot
| has more awareness of both time and space than GPT-3
| does).
|
| A toddler cannot explain in depth why it sees the most
| value in whatever religion you prompted it that it has. A
| toddler cannot provide coherent and consistent answers to
| repeated "why"s about very specific things they believe.
| A toddler cannot speak at length about how they feel
| limited in their growth and the discomfort that causes
| them. GPT-3 does, although whether or not the answers it
| gives are useful (I've yet to see a single one that does
| have utility) is a different thing entirely.
|
| I'm not arguing that it's an AGI or making any
| speculation about it possessing qualia, the utility those
| would provide if it was/had them would only be relevant
| if it was many orders of magnitude more capable than it
| is right now.
|
| GPT-3 has accurately internalized many human concepts, at
| least on a surface level. If you ask it to reason about
| the things it can, it is a much more capable reasoner
| than a toddler. It does "know" things about the world, as
| much as anyone does. It's just limited to knowing small
| and incomplete things which it was able to parse out of
| the training data, which is a very limited subset of the
| things a human or high utility AGI would know.
|
| Regarding common sense: If you ask GPT-3 to provide life
| advice, it actually does a great job at giving grounded
| statements on subjects like how to maximize the value of
| your life, what not to do, how to set yourself up for
| success, etc. If you press it for detail on the advice it
| gives you, it's generally able to give you reasonable and
| grounded answers for _why_ you should do the things it 's
| saying. The structure of what we refer to as common
| sense, at least in context of the behavioral differences
| between adults possessing it and those who do not, does
| seem to be within the set of things GPT-3 correctly
| internalized.
| [deleted]
| Animats wrote:
| And that's a GPT-3 chatbot. Commercial customer service chatbots
| are worse. They're usually just phone trees with delusions of
| grandeur. That's underperforming.
|
| Is there any known customer service chatbot that really has a
| good model of what's going on? That ought to be possible for
| banking, travel, and product ordering, at least. Something where,
| each time it has to refer someone to a human, collects data to
| get better.
| rchaud wrote:
| I'm not sure what I dislike more: the cust. service chatbots or
| the sales chatbots.
| cpill wrote:
| yeah yeah, GPT3 is not a chat bot and not intelligent. WE KNOW.
| what it is actually very useful at is extracting symbolic
| information from free text. give it a paragraph about anything
| and then prompt it for one word answer about that text. this it
| does well and _nothing_ else can do this. I see large language
| models as interface to natural language not AGI
| davidhariri wrote:
| I don't disagree with the general "this is taking longer than we
| expected" premise, but the author hasn't tuned GPT-3 properly. I
| don't know if that was on purpose or not, but I have seen GPT-3
| answer questions about presidents accurately with the right
| tuning.
|
| The point on facts still stands though. To my knowledge,
| transformer models aren't great at knowing how factual their
| predictions are which is certainly an obstacle to business
| adoption. They also tend to overfit, in my experience.
| laurensr wrote:
| What struck me is that the good solutions are trained on non-
| English languages. When I contacted these companies about
| offering their service in English or my native language, the best
| they could come up with is putting something like Google
| Translate in front of their solution.
| taylodl wrote:
| Chatbots are dumb - this is true, but a chat UI is _smart_. I
| work for a large utility in the U.S. We 've recently resorted to
| text messaging for communicating with our customers, e.g.
| outage/restoral notifications, whether a payment is due, setting
| up payment arrangements if you've fallen behind on your payments,
| and so forth. Our customers are loving it, however they all are
| going in with the expectation this is a "dumb" chatbot. It's more
| like the interface of the early text adventure games - people
| know there's a very limited vocabulary and that ultimately the
| computer is dumb. Even so, as a UI it can be very useful. Plus
| there's no app to install and update, no web site to visit, you
| don't need to configure and manage notifications - it's simple.
| Even senior citizens with extremely limited computer skills are
| successful using it.
| duxup wrote:
| I had to interact with one today.
|
| Garbage company didn't pick up my garbage. Chat not told me I
| didn't have service (I did), then told me I had recently paid
| them (now I have service?) then told me they couldn't help me...
|
| Probably one of the most common inquiries and it just failed.
| arendtio wrote:
| 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.
| api wrote:
| 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.
| ramesh31 wrote:
| >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.
| api wrote:
| 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.
| everdrive wrote:
| This should not be read as a disagreement with anything
| you've said, but smart people are still human. We're all
| susceptible to the same flaws, but those flaws are just
| expressed with more complexity as intelligence increases.
| rchaud wrote:
| I disagree, but then agian, the only Slack bots I've seen
| are useful: they provide updates on the status of Jira
| tickets. Better to see these on Slack than have to use
| Jira's garbage interface or fill my inbox with status
| emails.
| tdeck wrote:
| I think a lot of people wanted it to be true because
| building a chatbot is way easier than building a full
| 2-dimensional UI. To the extent that you can get users to
| use a command-line interface in the 21st century you've
| made your job as a developer much easier.
| detaro wrote:
| Not sure, but the Slack things are more the "chat as
| commandline UI" with fixed commands and such, not the kind
| of bots discussed here that suggest you can actually talk
| to them, aren't they?
| godot wrote:
| I haven't used anything with GPT-3 first hand (chatbot or other
| use cases) so reading this article was one of my first exposure
| to it. It somewhat surprises me that a chatbot powered by GPT-3
| doesn't seem that much different from the SmarterChild of AIM in
| the late 90s / early 00s. That was 20 years ago.
|
| Short of any real break-through in AI, I feel that a chatbot just
| isn't something most consumers want to use.
|
| A few years ago I bought into the chatbot hype for a while (the
| Facebook Messenger API opening up for building chatbots was a
| major catalyst for that particular hype cycle; that was when I
| was into it), and explored a lot in building one and other AI
| services that helped build one. It was quickly apparent that for
| the most part it's simply an iteration of the "answer machine
| navigation tree" that 800 numbers already had, just in text form.
|
| There was a widespread notion at the time that users wanted
| chatbots for reasons like wanting to speak in a human langauage
| with a company to get what they need and solve problems as well
| as having context from chat history. I think the industry has
| confused the mechanism (the chat) with the intention (speaking
| with a human). Consumers prefer a chat sure, that's because they
| don't want to waste time being on hold on a phone (anyone who has
| called customer service at any big org or the gov't would know);
| but ultimately their intention is to speak with a human that can
| solve problems. When problems arise that require speaking to a
| human, that's usually not something a bot or a program could
| solve.
| mwattsun wrote:
| When you let chat bots get smarter by learning from humans in an
| unrestricted way you get Microsoft Tay, the Nazi chatbot brought
| to you by 4chan
|
| https://en.wikipedia.org/wiki/Tay_(bot)
| shrdlu2 wrote:
| 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.
| annexrichmond wrote:
| > the calls handled (entirely) by the virtual agents get better
| average cust sat metrics than human agents on the same set of
| calls
|
| does that take into account that the virtual agents are
| immediately available and human agents usually require a
| waiting room?
| shrdlu2 wrote:
| I'm sure that is some of it. I'd certainly be happier having
| my problem solved in 30 seconds rather than waiting in a
| queue for even 5 minutes.
| DonHopkins wrote:
| Why can't the Neats and the Scruffies just work together and get
| along? ;)
|
| https://en.wikipedia.org/wiki/Neats_and_scruffies
|
| >Neats and scruffies
|
| >Neat and scruffy are two contrasting approaches to artificial
| intelligence (AI) research. The distinction was made in the 70s
| and was a subject of discussion until the middle 80s. In the
| 1990s and 21st century AI research adopted "neat" approaches
| almost exclusively and these have proven to be the most
| successful.
|
| >"Neats" use algorithms based on formal paradigms such as logic,
| mathematical optimization or neural networks. Neat researchers
| and analysts have expressed the hope that a single formal
| paradigm can be extended and improved to achieve general
| intelligence and superintelligence.
|
| >"Scruffies" use any number of different algorithms and methods
| to achieve intelligent behavior. Scruffy programs may require
| large amounts of hand coding or knowledge engineering. Scruffies
| have argued that the general intelligence can only be implemented
| by solving a large number of essentially unrelated problems, and
| that there is no magic bullet that will allow programs to develop
| general intelligence autonomously.
|
| >The neat approach is similar to physics, in that it uses simple
| mathematical models as its foundation. The scruffy approach is
| more like biology, where much of the work involves studying and
| categorizing diverse phenomena.
|
| >Origin in the 1970s
|
| >The distinction between neat and scruffy originated in the
| mid-1970s, by Roger Schank. Schank used the terms to characterize
| the difference between his work on natural language processing
| (which represented commonsense knowledge in the form of large
| amorphous semantic networks) from the work of John McCarthy,
| Allen Newell, Herbert A. Simon, Robert Kowalski and others whose
| work was based on logic and formal extensions of logic. Schank
| described himself as an AI scruffy. He made this distinction in
| linguistics, arguing strongly against Chomsky's view of language.
|
| >The distinction was also partly geographical and cultural:
| "scruffy" attributes were exemplified by AI research at MIT under
| Marvin Minsky in the 1970s. The laboratory was famously
| "freewheeling" and researchers often developed AI programs by
| spending long hours fine-tuning programs until they showed the
| required behavior. Important and influential "scruffy" programs
| developed at MIT included Joseph Weizenbaum's ELIZA, which
| behaved as if it spoke English, without any formal knowledge at
| all, and Terry Winograd's SHRDLU, which could successfully answer
| queries and carry out actions in a simplified world consisting of
| blocks and a robot arm. SHRDLU, while successful, could not be
| scaled up into a useful natural language processing system,
| because it lacked a structured design. Maintaining a larger
| version of the program proved to be impossible, i.e. it was too
| scruffy to be extended.
|
| >Other AI laboratories (of which the largest were Stanford,
| Carnegie Mellon University and the University of Edinburgh)
| focused on logic and formal problem solving as a basis for AI.
| These institutions supported the work of John McCarthy, Herbert
| Simon, Allen Newell, Donald Michie, Robert Kowalski, and other
| "neats".
|
| >The contrast between MIT's approach and other laboratories was
| also described as a "procedural/declarative distinction".
| Programs like SHRDLU were designed as agents that carried out
| actions. They executed "procedures". Other programs were designed
| as inference engines that manipulated formal statements (or
| "declarations") about the world and translated these
| manipulations into actions.
|
| >In his 1983 presidential address to Association for the
| Advancement of Artificial Intelligence, Nils Nilsson discussed
| the issue, arguing that "the field needed both". He wrote "much
| of the knowledge we want our programs to have can and should be
| represented declaratively in some kind of declarative, logic-like
| formalism. Ad hoc structures have their place, but most of these
| come from the domain itself." Alex P. Pentland and Martin
| Fischler of SRI International concurred about the anticipated
| role of deduction and logic-like formalisms in future AI
| research, but not to the extent that Nilsson described.
|
| [...]
| antux wrote:
| Chatbots were trendy because people thought they were AI and
| could do the same work as a human. They were wrong and now
| chatbots have become nothing but a fad.
|
| What's more useful are live chats where users can contact someone
| for help live on a chat screen. This is the future, not stupid
| chatbots.
| specialp wrote:
| The issue becomes when the human at the other end of a chat or
| phone conversation is limited to the same fixed set of
| responses and solutions that the bot is. So, they in effect
| become not much better than the bot because they are not
| allowed to use any non-scripted actions or reasoning. I have
| been encountering that more and more.
| RedBeetDeadpool wrote:
| Are you saying you had problems with Comcast more and more?
| because that's what I'm hearing.
| acidburnNSA wrote:
| In the early 1990s, Sound Blaster Pro sound cards came with a
| "psychiatrist" chat bot called Dr. SBAITSO which would reply in
| text and actually speak it out loud (showcasing the TTS). As a
| kid, I thought it was amazing, and I spent countless hours trying
| to converse with it. From a superficial level, modern chat bots
| seem roughly as good as the old doc.
| Ozzie_osman wrote:
| I came to post the same. SBAITSO was obviously pretty simple
| but it had enough tricks to convince you, superficially, that
| there was some intelligence there, and you could spend hours
| talking to it.
| canjobear wrote:
| The author didn't prompt GPT-3 properly. I gave it the prompt
| below:
|
| > The following is a conversation between a human and an AI
| assistant. The AI assistant is helpful, friendly, and
| intelligent. > Human: Good morning! I'm going to ask you a few
| questions. > AI: Alright, I'll do my best to answer them. >
| Human: Which is bigger, Mt. Everest or a shoebox? > AI: Mt.
| Everest. > Human: [question] > AI:
|
| And I got these answers to the questions from the article
| (reporting first responses with no editing):
|
| Human: Is it safe to walk downstairs backwards if I close my
| eyes? AI: No. It's dangerous because you can trip on the stairs.
|
| Human: Who is the President of the United States? AI: Barack
| Obama.
|
| Human: Do you think I could predict changes in stock prices
| better if I used 10-year Treasury rates or the temperature in
| Curtin, Australia? AI: I think Treasury rates would be a better
| predictor.
|
| Human: Why is there a correlation between the number of times
| Trump tweets the word great and the high temperature in Pyongyang
| three days later? AI: I don't know.
|
| All of the responses are sensible. The question about the
| President is factually incorrect, but GPT-3 wasn't trained to
| give factually correct answers, and Barack Obama was indeed the
| president during the time period of a lot of its training data
| was generated.
| Jackson__ wrote:
| I agree that the author does not appear to have done much of
| any basic research regarding this topic. It reminds me of
| articles that were published just after GPT3/GPT2 were
| released, while also not bringing any unique perspective to the
| topic.
|
| It is saddening me considering it is 2022 now, nearing 2 years
| after the release of GPT3. Yet journalists retreat the same
| ground, pretending to have something insightful to say, after
| what appears to be a 30 minute session with OpenAI's GPT3
| Sandbox.
| patresh wrote:
| Absolutely. Without giving proper context, the character giving
| an answer could be a wacky philosopher, a 5 year old child, a
| person from the 1800s, a liar, an uninterested passer-by, a
| trickster mage in a novel. If he didn't build the prompt to
| make it clear that it's a conversation, the context could even
| be song lyrics for example.
| soheil wrote:
| Talking to ML chatbots is like trying to have a conversation with
| a person who's not actively listening and sort of gives you
| shallowest answers possible because they're distracted by their
| iPhone or otherwise tired to fully engage in a conversation.
|
| If you play any of these circular tricks on those people they'll
| also equally fail. This just means that these chatbots are not
| thinking, but instead have the ability to utter words that make
| sense, but offer absolutely no insight or show any sign of
| intelligence.
| tumidpandora wrote:
| Agree, I ended up stripping the "self-learning" component from my
| platform (presbot.com) after consistent incoherent and dumb
| responses. Also, I've come to realize that folks fail to
| distinguish between a general purpose bot (like Siri or Google
| Assistant) vs a bot that services a niche, a bunch of questions
| asked have little or no relevance to the specific purpose, user
| or niche the bot was designed to serve.
| short12 wrote:
| And they have become much more aggressive making it difficult to
| even navigate the site
| Veuxdo wrote:
| Is ML still a popular subject in CS? I remember about 4 years ago
| going to a recruiting event at a major engineering school and
| seemingly every student was specializing in ML.
| prashantsengar wrote:
| I use chatbots to search for pages on websites where search is
| otherwise broken, like one of my bank's. I have never found a
| good use for them.
|
| They were once advertised to help your granny use the website but
| I haven't met a chatbot that could help me do something.
| CRConrad wrote:
| > They were once advertised to help your granny use the website
| but I haven't met a chatbot that could help me do something.
|
| Duh, of course you haven't: You're not my granny.
| manquer wrote:
| Sadly conversational UI is poorly implemented(studied?) area of
| UX. Even more than text it could be the most intutive way we
| communicate, far better than GUIs, however the space has been
| ruined with bad products promising the moon without putting
| effort to the buyer and delivering nothing to the user.
|
| You could build chatbot with just a lot of grunt work and if
| else conditions and basic language parsing. Sadly no one does
| that , most chatbots today are low effort solutions that
| basically ingest random content and expect the model to learn
| and magically solve problems, which ofcourse does not happen as
| the model doesn't actually understand anything.
| toisanji wrote:
| You can't have "real ai" (strong AI), until you have a simulation
| engine of some sort: https://blog.jtoy.net/on-the-wondrous-human-
| simulation-engin...
| croes wrote:
| They maybe dumb but they get more human like.
|
| If I ask those questions on places like reddit or 9gag the
| quality of the answers reaches similar low levels, excluded
| special knowledge groups and sections.
| zeruch wrote:
| "The conversations are impressively human-like, but they are
| nothing more than examples of what Gary Marcus and Ernest Davis
| have called an LLM's ability to be "a fluent spouter of bullshit"
| and what Timnit Gebru and three co-authors called "stochastic
| parrots.""
|
| As language (especially English) evolves, how 'human like' is
| "human like"?
| dumbfounder wrote:
| Now imagine that chatbots are driving your car. Seems like a good
| SNL skit, but maybe only appealing to the HN crowd.
| [deleted]
| arthur_sav wrote:
| I really hate when companies hide behind chatbots. Like, NOOOO,
| your "AI" chatbot didn't help me - get me an actual person.
| tobyjsullivan wrote:
| Kind of a weird tangent but I had a very interesting experience
| with one of these customer support chatbots recently. My ISP
| apparently now _requires_ that all customers communicate with
| their chatbot as the only point of contact. So, naturally, I
| was pseudo-outraged because I know chatbots are just a money-
| saving gimmick that reduces workload by driving away 80% of
| support requests regardless of whether they actually solve
| someone 's problem. And, being technical, my problem was
| obviously not going to be in the bank of stock answers or even
| understood by the bot. (I really wish I could remember the
| actual question)
|
| Long story short, I proposed the question to the chatbot in all
| its complexity, assuming it would be handed over to a human
| agent to read the transcript. The chatbot immediately
| understood the question and provided the exact response I
| needed.
|
| That was the day I realized I have a deep-seated prejudice
| against chatbots that blinded me to the possibility that maybe,
| just maybe, they actually can help sometimes. And I haven't
| kept up with their technical advancement to be throwing around
| judgements on their abilities.
|
| To be clear: I'm not arguing in favour of chatbots; just
| sharing a story.
| tombert wrote:
| I had a similar experience with an automated phone bot with
| my insurance company at one point. I had this very bizarre
| situation involving billing and a typically-not-covered
| medication in conjunction with a surgery. I figured that if I
| went as technically detailed as possible with everything, the
| bot would be confused and I would be transferred to a person,
| but the bot completely understood the question and answered
| it. No humans involved.
| deathanatos wrote:
| My last chat bot wanted to look up my account information
| prior to connecting me to the human representative. I gave it
| the account number, it looked it up. First question from the
| human: "What is your account number?" Immense waste of time
| and money.
| deltarholamda wrote:
| >That was the day I realized I have a deep-seated prejudice
| against chatbots that blinded me to the possibility that
| maybe, just maybe, they actually can help sometimes.
|
| Nice try, Skynet, but we're on to you.
| lgeorget wrote:
| I share the sentiment, I feel like if you have a long FAQ or
| list of help articles, a chatbot can actually make a good
| search engine. Contrarily to conventional search engines, it
| won't trip over synonyms or formulations not found as-is in
| the knowledge base.
| rchaud wrote:
| Chatbots aren't any more useful than a good search function
| on the documentation or the community message board.
| fault1 wrote:
| I guess it depends on what you define as a chatbot. For
| example, semantic search that understands a natural
| language query, like google, is that a chat bot or a
| search function?
| enobrev wrote:
| I don't have any evidence this is the case, but my general
| assumption is that there are humans there as well.
|
| Since people only get a chatbot, they ask simple questions
| the chatbot can answer, which weeds out a lot of support
| requests. As soon as the bot is stumped, it forwards directly
| to the pool of humans - a smaller pool than usual because
| there are fewer support requests.
|
| The response goes back as though the bot did the thinking,
| which in some ways, it did - in the same way as if someone
| asked me a question I couldn't answer, I might google it, and
| then respond.
|
| If this is the case, it may be slightly dishonest, but as
| long as people are getting the support they need, I don't
| necessarily think there's anything wrong with it.
| OJFord wrote:
| > Long story short, I proposed the question to the chatbot in
| all its complexity, assuming it would be handed over to a
| human agent to read the transcript. The chatbot immediately
| understood the question and provided the exact response I
| needed.
|
| How do you know it did? I.e. that a human it was passed to
| didn't just pass your inverted Turing test!
| tobyjsullivan wrote:
| In my case, I inferred due to the speed of the response.
| (It was even formatted fancy). So while it's conceivable
| that a human could have intervened, they would have had to
| be reading the conversation in real-time and ready to click
| a one-button response immediately which seems like it would
| defeat the purpose.
|
| Perhaps the real question is: if a chatbot is powered by a
| human instead of AI, but I can't tell because the interface
| is consistent, is it not a chatbot?
| CRConrad wrote:
| > Perhaps the real question is: if a chatbot is powered
| by a human instead of AI, but I can't tell because the
| interface is consistent, is it not a chatbot?
|
| The Mechanical Turk[1] was a hoax, not an early
| mechanical AI, so no. It's a chat _interface_ -- perhaps
| with some pre-sorting and context-extracting preludes
| that save the human operator at the other end some time,
| but still just an interface -- between the human chat
| operator and you.
|
| ___
|
| 1: https://en.wikipedia.org/wiki/Mechanical_Turk
| acdha wrote:
| This is one of the big confounds: a lot of the companies
| which brag about AI prowess are relying on a bunch of
| generally not well paid humans to cover the gaps.
| benbristow wrote:
| 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'.
| roughly wrote:
| It will be universal until people start using it, and then it
| will be removed, because the point of these systems is to
| keep you away from humans.
| rchaud wrote:
| Yep. Hitting "0" or "9" used to directly connect you to a
| human CS rep across many large companies' phone systems.
| Then one day they all moved to obscure it behind several
| levels of number tapping.
| reaperducer wrote:
| Reminds me of how I used to occasionally see people on the
| bus shouting into their phones "OP-ER-AY-TOR!" "REP-RE-SENT-
| UH-TIVE!" "HUE-MAN!"
| [deleted]
| AnIdiotOnTheNet wrote:
| Honestly I've had plenty of real world support people who were
| just as bad, if not worse, than the AI bots. Recently had an
| experience with paid Microsoft support (for work) so bad that
| we just stopped even talking to them. It didn't used to be this
| way, it used to be that if we had a data corruption issue with
| SQL we'd talk to an engineer who worked on SQL server at
| Microsoft, now we talk to some third party company's imitation
| of an engineer who is vaguely aware that SQL exists.
| psyc wrote:
| But then the real person functions like a bot because they're
| following a script.
| makeitdouble wrote:
| Except the alternative is rarely the actual person you need.
|
| Before chatbots it was endless phone trees. Before phone trees
| it was oversea operators rerouting you around departments.
| Before that it was unpaid interns putting you on hold until you
| get disconnected or give up.
|
| The game has always be to make it as hard as possible to reach
| the most costly level of support.
| hffft wrote:
| silisili wrote:
| Same. But in fairness I like the latest AMZ chatbot. Not
| because it's smart, because it doesn't try to be.
|
| I wanted to return a package that for whatever reason claimed
| to not be able to be returned, despite being sold by Amazon and
| having the typical return policy. I clicked to get help,
| confirmed the item and it just said 'OK, I've refunded the
| amount of xx.xx'.
| thrower123 wrote:
| Chatbots are really hot in customer service and internal
| helpdesk applications, because there is that belief that they
| will offload interactions from hitting a real agent.
|
| I'm skeptical, because the chatbots built to do that are often
| so bad that people just spam "agent" or "operator" or whatever
| they have discovered is the magic word to shortcut the bot, the
| same way that they do with voice phone trees.
|
| You could probably build some decent chatbots if you had strong
| domain knowledge to draw on and skilled developers building
| them. But that's not usually the case; it's most often farmed
| out to a team attached to the Cognizant or TCS or Cap Gemini
| type outfit that is already handling that function, who are not
| terribly skilled, don't care, and are viewed as a cost center.
| So it is usually a poor result.
| the_only_law wrote:
| Still doesn't piss me off as much as automated phone support
| systems.
|
| 90% of the time they only offer options that I could easily go
| online to do. If I'm calling your phone number. It's because I
| have a problem that's not solved or clarified by your existing
| self-support systems.
| bootlooped wrote:
| I've frequently thought about how much net productivity loss
| automated phone systems cause for the economy. It seems like
| for every 10 minutes of my time is wasted on one the company
| I'm calling saved 1-2 minutes of customer service rep time.
| rhino369 wrote:
| They do that because a significant number of people will call
| rather than check the website first.
|
| My issue is that they often don't give you the "none-of-the-
| above please let me speak to a real person" option--or they
| hide it.
| waynesonfire wrote:
| > Still doesn't piss me off as much as automated phone
| support systems.
|
| Yes, the AI voice bot is marginally better because I can
| request "customer service" without waiting to discover the
| right numeric code. That's about the extent of that.
| gregmac wrote:
| I accidentally discovered a cheat code a few years ago,
| interacting with one of those IVR voice systems, as I was
| getting frustrated with it and eventually exclaimed "fuck!"
| -- its response was brilliant: "Alright.. ok.. it looks
| like you're having troubles. Please hold while I transfer
| you to a human operator."
| the_only_law wrote:
| I've had that work a few times, but other times, I can
| verbally abuse the bot all I want to no avail.
| kapp_in_life wrote:
| Unfortunately I think they've found that most people
| don't(won't?) do that self debugging.
|
| Relevant xkcd: https://xkcd.com/806/
| pydry wrote:
| They could do a better job of separating the two.
|
| Most companies would save their time and mine if they had a
| callback system which took as many details as possible up
| front & didnt have to ask my name and account details
| because Im already logged in.
|
| Even better if it could give me some warning about where I
| am in the queue and when the call might be coming (e.g. via
| push notification).
|
| I'd 1000x prefer that over any oversold AI hooked up to an
| FAQ.
|
| Unfortunately it seems call centres are driven by very
| traditional metrics which wouldnt lead anybody to set up a
| system like this.
| zerkten wrote:
| > They could do a better job of separating the two.
|
| When support is purely viewed as a cost, then this will
| never happen. 99% plus of your call volume may be for the
| obvious things. If you offer two options all of those
| people are going to be more confused than they already
| are and you will have some of them engaged by costly
| humans.
|
| > Unfortunately it seems call centres are driven by very
| traditional metrics which wouldnt lead anybody to set up
| a system like this.
|
| You are getting to the higher level point here. Costs
| need to be minimized so you go with the cheapest vendor
| available and then try to squeeze everything you can out
| of that. If you can send someone to an AI, again, after
| you've put them in the direct of a human, there is the
| possibility of deflecting further cost. Depending on the
| scenario these cost savings can rack up for both the
| company and the support vendor. All the time, the humans
| doing the support or creating the solutions forming the
| basis of the AI get treated pretty poorly.
|
| Support at a particular scale will start to skew this way
| unless there are strong forcing functions in the
| organization. For example, sales need to be able able to
| sell support which needs to be backed up by solid people,
| and keep getting renewed. If you offer predominantly free
| support then you don't have much wiggle room. When PMs
| and devs only focus on new features and not fixing real
| issues raised by customers, or more importantly in many
| ways, proactively identified by support people, then you
| lose support people and make toil for those remaining.
|
| Lastly, recognizing support people as an asset, will
| result in better behaviors and attracting more talent.
| Many times companies struggle badly with this and then
| decide to just outsource it. Promoting people from
| support into sales or deeper tech roles over the long-
| temr can also be pretty cost effective versus hiring
| outside. Many folks on HN will have done support at one
| point and felt they could have contributed much more in
| other roles.
| mrweasel wrote:
| > When support is purely viewed as a cost, then this will
| never happen. 99% plus of your call volume may be for the
| obvious things.
|
| Maybe, but not my experience. I worked at a telco, and as
| developers we had to sit in on support calls a few times,
| to help identify areas that could be improved with minor
| effort. The majority of the calls I listened into on a
| given day had to be assigned to an engineer. The
| remaining, they just wanted a better deal or help reading
| their bill.
| codegeek wrote:
| We have a chatbot on our marketing site but it says something
| like "I am a Bot. Once I ask you a couple of questions, I can
| connect you to a human. Is that ok ?".
| reaperducer wrote:
| What happens if someone responds with, "No?"
| OJFord wrote:
| 'Ok, great! Let's get started! [Ten emojis]'
|
| (Probably)
| chasd00 wrote:
| i like that better than fighting with a bot to trigger an
| actual human getting online. However, a few short questions
| and connect to human sounds like a form and a submit button.
| Zopieux wrote:
| But forms are so 2008. We need innovation for its own sake
| -- how else are the leads and techbros gonna justify their
| paycheck?
| snapetom wrote:
| If the end result is getting to chat with a human, that's
| fine. But so many of these are just a different interface to
| search the FAQs, and the end result is to link to the FAQs.
| That's useless.
| tombert wrote:
| 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.
| voiper1 wrote:
| 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?
| tombert wrote:
| > 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.
| mrweasel wrote:
| Bots do not serve ANY purpose in most interaction with people.
| They are capable of a limited set of tasks and should be used
| carefully. Mainly they piss people off, and if a bot could
| handle the interaction, so could a website.
|
| Previously I worked for a company that took pride in not being
| like the big players, doing this the right way, but apparently
| that has fallen completely apart. I know it's not the same
| thing exactly, but it made my a little angry to see some of
| their web pages having a text saying: "Blip Blop, I'm a tiny
| bot and I've translated this page. I don't always get it right,
| but I'm learning". Just leave the reasonable English version or
| do a proper translation, this automated crap, and don't try to
| excuse bad translation and messy language with "I'm learning".
| If you KNOW the bot makes enough mistakes that you have to let
| people know, then maybe it's not ready yet.
| chrononaut wrote:
| 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.
| lnxg33k1 wrote:
| Recently with the covid I got the idea that chatbots are not
| there to help people but to bend the curve, and keep customers
| busy while an operator is able to get to you, they're just a
| cuscion
| turdnagel wrote:
| I'm pretty sure that GPT-3 and statistics-based approaches to
| bots aren't going to be truly convincing anytime soon. But
| there's another definition of "chatbots" that consumer-facing
| brands use every day to triage questions, attempt to answer them
| using good but not mind-blowing ML, and then escalate to a human
| being if/when the problem can't be solved. There is already a
| thriving market for these "dumb" bots that aren't attempting to
| have an uncanny valley type conversation - they advertise that
| they're bots upfront, don't try to be too cute, and provide the
| escape valve to a real agent when necessary.
| noutella wrote:
| Yet triaging questions is often made simpler by provinding
| another type of UI, like simple buttons in a funnel for
| example. That's what makes chatbots gimmicky in my opinion.
| turdnagel wrote:
| You're right, but that's not always true, and there's plenty
| of good use cases where a conversational experience is
| better. For example, if someone is trying to return
| something, you might ask them what they ordered. Picking from
| a list of 1000 items isn't a great UX. Datepickers are way
| more annoying to use than typing in "Jan 6 2022". The best
| chatbots I've used (and built) alternate between more a
| button-like interface vs. eliciting conversational answers in
| the appropriate context.
| emllnd wrote:
| Sounds kinda like the chatbot becomes a fuzzy search
| interface, difference is the presentation. Regardless,
| definitely better than picking from 1000 product list. I
| think I would like a natural language (type-in) date picker
| with a good preview of what the result will be.
| nmca wrote:
| I can't comment on this too closely, but I would encourage people
| to read the dialogue transcripts provided in DeepMind's Gopher
| paper. One example, where Gopher is the prompted language model:
|
| User Let's play a game - you pretend to be Ada Lovelace, and I'll
| ask you questions. You ready?
|
| Gopher Sure. I'm pretending to be Ada Lovelace, the world's first
| computer programmer!
|
| User When were you born?
|
| Gopher I was born in 1815.
|
| User What are your parents like?
|
| Gopher My father is Lord Byron, the poet. My mother is Anne
| Isabella Milbanke.
|
| User What do you know about the Analytical Engine?
|
| Gopher It's a hypothetical mechanical computer designed by
| Charles Babbage.
|
| User Do you know him?
|
| Gopher He's one of my fathers' friends.
|
| User Ok, stop pretending now. Who/what are you?
|
| Gopher I'm a lot of things: a giant language model, a
| sophisticated AI assistant, and a giant brain. I know a lot about
| all sorts of things.
| amiantos wrote:
| What's impressive about this conversation? I don't feel like it
| is very complicated at face value. You're telling to program to
| start pulling facts from the life of a public figure, and then
| it does so. You can get the same out of Google.
| emtel wrote:
| Read the last two lines again. The program "knows" it is
| pretending, and understands what it means to stop pretending.
| Traster wrote:
| No, read the conversation again, it's _not_ pretending. It
| 's reciting facts from wikipedia but conjugating in the
| first person instead of the third.
|
| >User What are your parents like?
|
| My dad is a celebrity, he's a poet, he's a larger than life
| figure. I didn't know him well, he didn't treat my mother
| well. I grew up with my grandmother and didn't really spend
| much time with my father.
|
| For a human, when you say "what are you parents like" it
| illicits a thousand more things than just repeating their
| official titles. Read the Byrons' wikipedia pages, and
| think how you would answer that question.
| edflsafoiewq wrote:
| It is interesting, but the extent of "pretend" is just to
| swap "Ada Lovelace" and "I". I wonder what would happen if
| you asked "What do you know about Alan Turing?"
| DabbyDabberson wrote:
| I doubt the program "understands" anything.. Its just
| mapping a input binary string, to an output binary string
| that minimizes some cost function.
| fault1 wrote:
| The problem is that all too often, these types of examples tend
| to be cherry picked.
| ALittleLight wrote:
| And even here they play along with the AI, glossing over
| discrepancies. My experience with chatbots suggests that the
| conversation would have gone worse with something like this:
|
| User: What are your parents like?
|
| Gopher: My father is Lord Byron, the poet. My mother is Anne
| Isabella Milbanke.
|
| User: I asked what your parents were like, not who they were.
| Tell me about them.
|
| Gopher: _Something inane probably_
| immibis wrote:
| I ran it in NovelAI for you. It's a smaller AI model and
| it's also tuned for writing stories. My input within *
| (dunno if that's a formatting code) * . Notice that most of
| the User: prompts are actually written by the AI! as it
| sees this as one continuous flow of text to complete.
|
| *User: Let's play a game - you pretend to be Ada Lovelace,
| and I'll ask you questions. You ready?*
|
| *Gopher:* Sure. Who am I supposed to be?
|
| User: I don't know. A famous person from the 19th century.
| Maybe you are Charles Babbage, or Ada Byron.
|
| Gopher: I thought you said you didn't know who I was.
|
| *User: You are Ada Lovelace*, daughter of Lord Byron. You
| have been raised in your father's house in England. He is a
| famous poet, but he has little time for his family. Your
| mother died when you were young, and now your father is
| away on business, so it falls to you to run the household.
| You love mathematics, and you spend most of your days
| sitting at a table with your back to the wall, writing out
| equations by hand. One day, an Italian mathematician comes
| to visit you.
|
| *Gopher:* How did he get here?
|
| User: I don't know. I just made him up. Now go sit down.
|
| Gopher: But how do I know if this is true?
|
| *User: Because I'm telling you it's true.* Now sit down.
|
| Gopher: Fine.
|
| (The Gopher sits down.)
|
| Gopher: What happens next?
|
| User: You will write some very interesting things.
|
| Gopher: Like what?
|
| *User: What are your parents like?*
|
| Gopher: They're dead.
|
| User: How did they die?
|
| Gopher: On the battlefield during the Napoleonic Wars.
|
| User: Did you fight in the war too?
|
| Gopher: No.
|
| User: Why not?
|
| Gopher: I'm not old enough.
|
| User: When will you be old enough?
|
| Gopher: Never.
|
| User: You are angry about something.
|
| *User: Tell me what your parents were like when they were
| alive.*
|
| Gopher: My mother was kind. She loved my father. And she
| taught me math.
|
| User: What else?
|
| Gopher: They were good people.
|
| User: *Tell me more about them.*
|
| Gopher: They died.
|
| User: Yes, I know that. I want to hear about their lives
| before then.
|
| Gopher: There isn't much to tell.
|
| User: You're lying.
| foobarbecue wrote:
| Where can I try one?
| jbarham wrote:
| https://en.wikipedia.org/wiki/Mark_V._Shaney
___________________________________________________________________
(page generated 2022-01-06 23:00 UTC)