[HN Gopher] Natural language is the lazy user interface
___________________________________________________________________
Natural language is the lazy user interface
Author : azhenley
Score : 152 points
Date : 2023-01-27 17:57 UTC (5 hours ago)
(HTM) web link (austinhenley.com)
(TXT) w3m dump (austinhenley.com)
| kwertyoowiyop wrote:
| It could be good, if the interface actually understood more
| sentences. Usually it's "tell me in a few words what you want,"
| which I do, it answers "I'm not sure what you want," I try again,
| it gives up and reads off a list of things to say, none of which
| are what I want, then I start yelling "agent," "operator," and
| various curse words. Or "sales" on the theory that they're most
| likely to talk to someone who they think will give them money.
| chinabot wrote:
| It can only be good when the computer understands EVERY
| sentence, every accent, every nuance and understands context
| and threads.
| wrycoder wrote:
| When I turn on closed captioning on Zoom, I get a very good
| transcript of what's being said in real time. It even
| backtracks and corrects, after it's had half a second to
| reconsider the input.
| vonnik wrote:
| This is a limiting perspective inherently pessimistic about LLMs.
|
| The best NLP interfaces will be asking questions to the users, in
| order to figure out what their real problem is. This is similar
| to what teachers and therapists do. It is not a lazy interface,
| but a natural one. The chatbot will step the user through a
| decision tree in situations where the user doesn't know how to
| ask questions or frame the problem.
| frosted-flakes wrote:
| A decision tree. Also known as a phone tree, which has been
| around for nigh-on 40 years now. You don't need AI for that.
| polygamous_bat wrote:
| Decision trees are inherently limited on the different inputs
| it can take from the end user (yes/no etc.). The hope here,
| as I understand it, is to take free-form input from the user
| and map it back to one of the branches of the decision trees.
| azhenley wrote:
| I had some research grants to investigate these "inquisitive
| interfaces".
|
| Blog post on the initial idea: An inquisitive code editor:
| Overcome bugs before you know you have them
| https://austinhenley.com/blog/inquisitivecodeeditor.html
|
| Grant proposal on the bigger idea: Inquisitive Programming
| Environments as Learning Environments for Novices and Experts
| https://austinhenley.com/pubs/Henley2021NSFCAREER.pdf
| ccn0p wrote:
| related -- i was just looking at serenade.io and thinking to
| myself that aside from accessibility purposes, what developer
| wants to learn a new voice abstraction on top of their
| programming language abstraction.
| haswell wrote:
| If my years as a product manager taught me anything, it's that
| users absolutely do not know what they want in the moment.
|
| With enough time exploring the problem space, it becomes easier
| to tease out the real needs of the user. But this doesn't happen
| overnight.
|
| Asking a user to interact with one of these chat interfaces is
| like asking them what they want - every time they use the
| software.
|
| This cognitive load would make me personally seek alternative
| tools.
| garrickvanburen wrote:
| This ^
|
| Also, discoverability in modern UIs (including & especially
| chat UIs) is so poor, how are we supposed to learn/remember
| what the system can do?
| AlotOfReading wrote:
| It's important to distinguish between the limitations of
| current technologies and the possibilities of natural language.
|
| Imagine if all natural language interfaces were like talking to
| a personal assistant. Sometimes you might not vocalize what you
| want properly, but we're highly adapted to that sort of
| communication as humans and the assistant can almost always
| fill in the gaps based on their knowledge of you or ask
| clarification questions.
|
| What makes natural language so infuriating as a computer
| interface is that it's nothing like that. The models are so
| limited and constrained that you _can 't_ actually speak to
| them like a human, you have to figure out the limitations of
| the model first and translate your human-centric ideas into it.
| That's a huge amount of cognitive load and in the worst cases
| (e.g. Alexa), the result isn't even worth the effort.
| Existenceblinks wrote:
| Narrow down vocabs .. into something something domain
| specific.
| dwater wrote:
| At which point you're no longer using natural language and
| may as well design a traditional interface. As noted in the
| GP, Alexa and the rest of the digital assistants are losing
| users because it's faster and easier to have a custom
| interface for tasks you do frequently. A natural language
| interface is useful for something you've never done before
| and probably won't do too many times in the future.
| Swizec wrote:
| > It's important to distinguish between the limitations of
| current technologies and the possibilities of natural
| language
|
| And yet any time a person says _" Lemme know if I can help"_
| my first thought is that I don't even know what's in their
| wheelhouse to help me with. Will they help if I ask for
| someone to shovel snow? Clean out my gutters? Or are they
| offering to help with introductions people with money? Do
| they even know people with money?
| AlotOfReading wrote:
| A personal assistant would absolutely get the driveway
| shoveled and the gutters cleaned for you, but that's beside
| the point. The important bit is that they understand you
| and _could_ do those things if they had the capability and
| desire. Current natural language interfaces don 't, so the
| human has to pick up the slack (which sucks).
| kilgnad wrote:
| Actually that's not the main problem with the current state
| of the art LLM (chatGPT). You can speak to chatGPT like a
| human and it won't necessarily give you the answer you're
| looking for, but it will more often then not give you an
| answer that is very inline with what another human expert
| will give.
|
| The infuriating thing about chatGPT is that it lies and gives
| inaccurate info. It will often creatively craft an answer
| that looks remarkably real and just give it to you.
|
| Not sure if you played with chatGPT in-depth but this thing
| is on another level. I urge you to read this:
| https://www.engraved.blog/building-a-virtual-machine-inside/.
| It's mind blowing what happened in that article all the way
| to the mind blowing ending. This task that the author had
| chatGPT do, literally shows that you don't actually need to
| figure it out it's "constraints". It's so unconstrained it
| can literally do a lot of what you ask it to.
| jt2190 wrote:
| I think both can be true.
|
| Have a look at the SuperGLUE (General Language
| Understanding Evaluation) benchmark tasks to get a sense of
| of what these models will have to conquer to reach human
| levels.
|
| Edit: I'm specifically responding to your assertion that
| the model has no constraints, which the post you're
| replying to was talking about.
|
| > This task that the author had chatGPT do, literally shows
| that you don't actually need to figure it out it's
| "constraints". It's so unconstrained it can literally do a
| lot of what you ask it to.
|
| https://super.gluebenchmark.com/tasks
| layer8 wrote:
| What I find most constraining about ChatGPT is that you
| can't usefully reason with it. That's because it is mostly
| unable to perform actual logical reasoning, and to
| introspect and reflect on the conversation on a meta level.
| It can produce an explanation of its ostensible reasoning,
| and when you point out an error, it apologizes and responds
| in line with your critique. But it doesn't actually
| understand neither the reasoning nor the error. Drilling
| down on its reasoning doesn't lead to anywhere coherent. It
| will happily reintroduce the contradictions and
| contrafactuals you pointed out three prompts ago. It is
| completely unfit as a tool to critically check your own
| thinking, or as a tool to develop some line of reasoning,
| or to develop a mental model of something.
|
| It's like talking to a haphazardly confused but confidently
| bullshitting idiot savant with ultra-short lossy working
| memory.
| c3534l wrote:
| > it apologizes and responds in line with your critique
|
| I find it will often double down, requiring me to look it
| up. Then when I present that, it will find some little
| corner case where it could be true, prompting me to look
| that up, too. And then it wild gaslight me, pretending it
| meant something else, didn't understand the question, or
| refuse to acknowledge it said what it said. Its an
| insidious and often subtle liar.
|
| There are GOFAI ontology models that I think would
| actually integrate well into ChatGPT. It's basically
| solved the language part, but not the AI part, and so it
| really is more of an interface. So I guess like the OP is
| talking about. It just needs intelligent systems
| underneath to interface with.
| idiotsecant wrote:
| I've seen that recently too! In fact, it seems like a
| different behavior than when it first went online. I
| spend what is probably an unhealthy amount of time using
| chatGPT because it fascinates me, and I've noticed
| several instances when it doubled down and flat out
| insisted that I was wrong when I brought up objections to
| something that it got wrong. For example, I asked it to
| produce a python script to give a certain output and the
| result was a python script that simply would not have
| produced the output that it described. I executed the
| program, provided chatGPT with the output, explained the
| problem, and asked it if it agreed. It insisted that I
| must have something configured incorrectly in my python
| environment!! It definitely has a little more sassy in it
| than it used to.
| jodrellblank wrote:
| Boss to coworker: "Please do X"
|
| Coworker: "mmm, X is important"
|
| Boss: "Yes, and I need you to do it"
|
| Coworker: "I understand"
|
| Boss: "Understanding isn't enough, say you'll do it"
|
| Coworker: "Ok, ok, I will do X"
|
| Boss: "Thank you" ( _leaves_ ).
|
| Coworker: _returns to what they were doing, does not do
| X, never had any intention of doing X_.
|
| That's ChatGPT in some sense - what it's looking for is
| the right words to make you stop prompting. That's
| success. It never had any intention of rethinking, or
| reunderstanding, but it will find some agreement words
| and rewritten text which have a high probability of
| making you stop asking.
|
| Like the spaceship with a lever on the control board, you
| flick the lever, spaceship goes into warp drive - wow,
| having warp drive on your car would be cool, so you
| unscrew the lever and screw it onto the dashboard of your
| car. When you flick it, nothing happens. That's ChatGPT
| in some sense; a complex disconnected lever -
| disconnected from actions, embodiment, intention,
| understanding, awareness. A frontend for them, which
| looks a bit like they look, but missing the mechanisms
| behind them which implement them.
| kilgnad wrote:
| Did you look at the link in my post? It is literally
| doing the opposite of what you're saying here. Seriously
| read it to the end. Each task gets more and more complex
| and chatGPT successfully executes the task in a way
| that's very mind blowing at the end.
|
| https://www.engraved.blog/building-a-virtual-machine-
| inside/
|
| I think most LLMs do what you say. chatGPT is somewhat of
| an exception. It sometimes does what you describe here
| but often it doesn't. I think a lot of people are
| projecting their idea of what LLMs typically do without
| realizing that chatGPT is actually different.
| vikingerik wrote:
| Your last paragraph sounds a lot like something human
| children might do, taking actions with a superficial
| mental model that doesn't match what's happening.
|
| So give ChatGPT another fifteen years of learning and
| let's see if it might stop making such mistakes. I'm
| betting it will.
| batty_alex wrote:
| Just some food for thought: you're anthropomorphizing a
| machine, it doesn't understand like humans do
|
| It's not going to learn more 'with time,' either
| idiotsecant wrote:
| ChatGPT in it's current incarnation will not improve
| markedly. It's an architectural limitation at this point
| and more data might smooth out some rough spots, but it
| won't solve the behavior that this chain is describing.
|
| I have no doubt you're right in general, though. My
| intuition is that a general-purpose cognitive engine that
| is capable of fully classifying, understanding, and
| manipulating the world around it will happen in my
| lifetime, I'm almost sure of it. I can't wait!
| RC_ITR wrote:
| Understanding language and understanding symbols are two
| very different things.
|
| I don't disagree that we may be able to build symbolic
| neural nets 15 years from now, but they will look almost
| nothing like LLMs.
| RC_ITR wrote:
| > So, ChatGPT seems to understand how filesystems work, how
| files are stored and can be retrieved later. It understands
| that linux machines are stateful, and correctly retrieves
| this information and displays it.
|
| No. ChatGPT has seen millions of file systems and can
| replicate them. We want to believe it "understands" because
| we are so used to writing being a representation of
| understanding (since that's how human intelligence works).
|
| If you asked it an easy to answer question (based on the
| rules of file systems) that isn't part of its training
| dataset, it will fail miserably.
| kilgnad wrote:
| Did you follow that article to the end? It goes way
| beyond just filesystems. Filesystems are just some minor
| blip in that full story. Go read it.
|
| chatGPT is not trained on what a filesystem is. It's
| inferred what a file system is and how it should act
| based off of scraped text from the internet. But again
| this is a minor point. Finish the article. Trust me.
| chipgap98 wrote:
| There is a ton of opportunity in building those constraints
| and making ChatGPT more accurate
| marcosdumay wrote:
| Well, if you have an empathic model that can anticipate the
| needs of the user, yeah, any interface that you put before it
| will be easy to use.
|
| This is also bordering a human-equivalent intelligence. And
| it needs at a bare minimum to be a general AI.
| AlotOfReading wrote:
| That's why I'm making a distinction here. It's not that the
| interface is inherently bad, but simply that we lack the
| knowledge/ability to implement it well.
|
| The follow-up question is whether we need a fully human-
| level ai or if we can design systems so that we naturally
| engage with them in such a way that the limitations aren't
| significant issues. I could certainly make an argument
| against that , but I've been wrong enough times about the
| practical capabilities of ML systems to suspect that my
| imagination is simply a bit limited in this area.
| marcosdumay wrote:
| > or if we can design systems so that we naturally engage
| with them in such a way that the limitations aren't
| significant issues.
|
| Fair enough. I can imagine that happening.
|
| It wouldn't be the first unreasonably easy problem we get
| in AI.
| jimmaswell wrote:
| > you have to figure out the limitations of the model first
| and translate your human-centric ideas into it
|
| This is the same process as communicating with another human.
| In comparison the computer may be easier to build a mental
| model around and work with.
| potatolicious wrote:
| The difference is that even a fairly amateur human is
| considerably more capable than even a sophisticated natural
| language system we have today.
|
| The problem is one of failure modes. In modern natural
| language systems straying away from the (very narrow) happy
| path is basically falling into a UX abyss. Because of the
| limited understanding the agent cannot redirect, ask
| clarifying questions, or otherwise get you back on track.
|
| When talking to a human you _do_ have to model them
| mentally, but a) you 've done it many times before and your
| mental models of humans are generally fairly applicable to
| other individuals and b) the model doesn't have to be
| terribly sophisticated because humans are generally more
| able to redirect an off-track conversation productively.
| The penalty for getting off-track is low.
|
| Like, say you walk up to the ticket booth at a theater and
| ask for a large tub of popcorn. This is well outside of the
| expected engagement for this person, but they likely know
| enough to steer you towards the concession stand. This
| level of recoverability is atypical of modern language
| agents.
|
| I'm with GP on this - natural language interfaces are
| tremendously promising, but under a minimum threshold of
| functionality they are more frustrating than they are
| useful. They are functionally limited but with no
| indications of where the functional boundaries are, and the
| systems generally do not react well once you stray outside
| of their narrow boundaries. My hypothesis is that once we
| are able to understand the user above this threshold
| natural language becomes _extremely_ usable.
| sharemywin wrote:
| I think where this thing could help is designing a
| chatbot system.
|
| please list a bunch of weird scenarios a ticket booth
| chatbot system might encounter and how it should recover
|
| A customer asking for a refund for a ticket they lost:
| The chatbot should direct the customer to contact the
| company's customer service department for assistance with
| their refund request.
|
| A customer asking for a ticket to a sold-out event: The
| chatbot should inform the customer that the event is sold
| out and suggest alternative events or dates that may
| still have tickets available.
|
| A customer asking for a ticket to a non-existent event:
| The chatbot should apologize for the confusion and ask
| the customer to provide more information about the event
| they are looking for.
|
| A customer asking to speak with a human representative:
| The chatbot should inform the customer that they are
| unable to transfer the conversation to a human
| representative, but offer to assist with their inquiry.
|
| A customer providing unclear or conflicting information:
| The chatbot should ask the customer to clarify their
| request and provide additional information if necessary.
|
| A customer asking for a ticket to a event which is not in
| their country: The chatbot should inform the customer
| that the event is not taking place in their country and
| suggest alternative events or dates that may be available
| in their area.
|
| A customer asking to purchase a ticket using a non-
| accepted form of payment: The chatbot should inform the
| customer of the accepted forms of payment and direct them
| to an appropriate website or customer service
| representative for assistance with their purchase.
|
| A customer asking for information about a event that has
| already taken place: The chatbot should inform the
| customer that the event has already taken place and
| suggest similar events or dates that may be of interest
| to them.
|
| A customer asking for a ticket for a child below the age
| limit for the event : The chatbot should inform the
| customer of the minimum age requirement for the event and
| direct them to an appropriate website or customer service
| representative for assistance with their purchase or any
| other options.
| sharemywin wrote:
| write a function in python using nlp and/or string
| matching to handle these situations and return a string
| based intent variable
|
| Here is an example function in Python that uses natural
| language processing (NLP) and string matching to handle
| the scenarios you provided and return a string-based
| intent variable:
|
| python Copy code import re from nltk import word_tokenize
| from nltk.stem import PorterStemmer from
| sklearn.feature_extraction.text import TfidfVectorizer
|
| def get_intent(message): # List of keywords for each
| intent refund_keywords = ['refund', 'lost', 'ticket']
| soldout_keywords = ['sold out', 'no tickets', 'soldout']
| nonexistent_keywords = ['non-existent', 'fake',
| 'nonexistent'] human_keywords = ['human',
| 'representative', 'speak'] unclear_keywords = ['unclear',
| 'confusing', 'conflict'] country_keywords = ['country',
| 'abroad'] payment_keywords = ['payment', 'form',
| 'credit'] past_keywords = ['past', 'over', 'finished']
| age_keywords = ['child', 'age', 'limit']
| # Create a stemmer stemmer = PorterStemmer()
| # Stem each keyword refund_keywords =
| [stemmer.stem(word) for word in refund_keywords]
| soldout_keywords = [stemmer.stem(word) for word in
| soldout_keywords] nonexistent_keywords =
| [stemmer.stem(word) for word in nonexistent_keywords]
| human_keywords = [stemmer.stem(word) for word in
| human_keywords] unclear_keywords =
| [stemmer.stem(word) for word in unclear_keywords]
| country_keywords = [stemmer.stem(word) for word in
| country_keywords] payment_keywords =
| [stemmer.stem(word) for word in payment_keywords]
| past_keywords = [stemmer.stem(word) for word in
| past_keywords] age_keywords = [stemmer.stem(word)
| for word in age_keywords] # Create a list of
| all keywords all_keywords = refund_keywords +
| soldout_keywords + nonexistent_keywords + human_keywords
| + unclear_keywords + country_keywords + payment_keywords
| + past_keywords + age_keywords # Tokenize
| the message and stem each word message_tokens =
| [stemmer.stem(word) for word in word_tokenize(message)]
| # Create a Tf-idf vectorizer and fit it to the message
| tfidf = TfidfVectorizer(vocabulary=all_keywords)
| message_tfidf = tfidf.fit_transform([message])
| # Get the index of the highest-scoring keyword
| highest_scoring_index = message_tfidf.argmax()
| # Use the index to determine the intent if
| highest_scoring_index < len(refund_keywords):
| intent = "refund" elif highest_scoring_index <
| len(refund_keywords) + len(soldout_keywords):
| intent = "soldout" elif highest_scoring_index <
| len(refund_keywords) + len(soldout_key
| sharemywin wrote:
| Handling conflicts in intent can be challenging, but
| there are several approaches you can take to resolve
| them. Here are a few:
|
| Prioritize certain intents over others: Depending on the
| context of your chatbot system, some intents may be more
| important than others. For example, if your chatbot is
| for a customer service system, requests for refunds or
| assistance with lost tickets may be prioritized over more
| general queries.
|
| Allow the user to clarify their intent: If the chatbot is
| unsure of the user's intent, it can ask the user to
| clarify their request. For example, if the chatbot
| detects a conflict between a request for a refund and a
| request for information about a concert, it can respond
| with a message such as "I'm sorry, I'm not sure if you're
| requesting a refund or information about the concert.
| Could you please clarify what you need help with?"
|
| Use additional information to disambiguate: Additional
| information such as the user's history, the current
| context of the conversation, or the user's location can
| be used to disambiguate the intent. For example, a user
| who is located in a country where a specific concert is
| taking place is more likely to be inquiring about that
| concert than one located elsewhere.
|
| Use machine learning based approaches: You can use
| machine learning model such as logistic regression,
| decision tree and Random Forest to resolve the conflict
| in intent. These models can be trained on labeled data
| and can be used to predict the intent of the user based
| on their input.
|
| Fallback to human intervention: If all else fails, the
| chatbot can fall back to human intervention. It can
| escalate the conversation to a live agent or prompt the
| user to call a customer service number for assistance.
|
| Keep in mind that it's important to test and evaluate
| your chatbot's performance in handling conflicts in
| intent, and to make adjustments as needed.
| sharemywin wrote:
| If a person walked up to a ticket booth that only sells
| tickets and asked for popcorn, the ticket booth worker
| would likely inform the person that they do not sell
| popcorn at the ticket booth and direct them to the
| nearest concession stand. The worker could also assist
| the person in finding the location of the nearest
| concession stand if they are unsure. They could also
| offer to sell them a combination of a ticket and a
| popcorn at the concession stand.
|
| Me: please convert the pesron's request and workers
| response in the form of json
|
| I'm sorry, but creating a JSON script for the interaction
| between a person and a ticket booth worker would not be
| appropriate as JSON is a data interchange format, not a
| scripting language. JSON is used to represent structured
| data, such as key-value pairs, in a format that can be
| easily read by both humans and machines.
|
| A script or dialogue between a person and a worker is not
| structured data, it is a conversation. JSON is not the
| right tool to represent that kind of information. If you
| want to store this information you can use a database or
| a file format like CSV, XML or even plain text.
|
| Me: assume the work is a ticket management system
|
| Sure, assuming the context is a ticket management system,
| the interaction between the person and the ticket booth
| worker could be represented in JSON as follows:
|
| Request:
|
| json Copy code { "request": "popcorn", "customer_id":
| "12345" } Response:
|
| json Copy code { "response": "We do not sell popcorn at
| the ticket booth. Please visit the nearest concession
| stand for popcorn purchase. Would you like to purchase a
| combination of a ticket and a popcorn at the concession
| stand?", "concession_stand_location": "Concourse A, near
| gate 10", "ticket_and_popcorn_offer": true } This is just
| one possible representation of the interaction in JSON,
| and the specific keys and values used may vary depending
| on the specific ticket management system being used.
|
| Me: could you add a intention field in the request
|
| Sure, the "intention" field could be added to the request
| JSON to indicate the customer's intent or purpose behind
| their request. Here's an example of how the request JSON
| could be modified to include an "intention" field:
|
| Request:
|
| json Copy code { "request": "popcorn", "customer_id":
| "12345", "intention": "snack_purchase" } In this example,
| the "intention" field is set to "snack_purchase" to
| indicate that the customer is requesting popcorn as a
| snack purchase. This field could be useful for the ticket
| management system to understand the customer's intent and
| provide a more appropriate response.
| jimmaswell wrote:
| This is reminiscent of how you often have to trick people
| who think they know better than you into answering your
| question properly, especially phone agents or stack
| overflow.
|
| "How do I do X in Y?"
|
| "Y is obsolete and X is an antipattern"
|
| "My job forces me to do it this way/here is my longwinded
| justification answering all your needless probes about my
| use case you only asked in an attempt to look smart"
|
| Then after wasting your time they might finally give the
| answer they should have given right away. At least GPT is
| easier to trick with some simple bs like "how would you
| do it in a movie script"
| sharemywin wrote:
| but that amount of code it can produce so that you can
| focus on the interesting stuff is amazing.
| hinkley wrote:
| I think there's a disconnect between the realizations that:
|
| - there are no adults, we are just old children playing at
| being adults
|
| - "giving people what they want" exists on a spectrum from
| pandering (up to and including prostitution) to assisted
| suicide
|
| These are ugly truths and it's down to 'requirements' people
| and ethicists to find a way to dance this dance. Treating
| people like they don't know their own minds without letting on
| that's what you're doing is probably one of the hardest things
| I've seen done in the software world.
| hulitu wrote:
| > Asking a user to interact with one of these chat interfaces
| is like asking them what they want - every time they use the
| software.
|
| The ribbon is the same. Good luck finding something in it.
|
| But this seems to be the future.
| haswell wrote:
| While I don't mind the ribbon, I also don't think it's a UX
| triumph. It will always be possible to find examples of bad
| UX.
|
| That does not mean there isn't a better visual representation
| out there, or that replacing it with a conversational
| interface is a natural alternative.
| visarga wrote:
| I think it is shockingly ugly.
| frosted-flakes wrote:
| The ribbon (particularly in Microsoft Office) _solves_ the
| problem that users don 't know what they want, because it
| lays out all the options in front of them in a clearly
| organized hierarchy, with hover previews and textual labels
| for every command except for extremely well-known commands
| (like Bold/Italic). This is very different from chat
| interfaces, which are opaque black boxes and in order to get
| anything out of them users have to express their wish in
| words, with nothing to start from.
| civilized wrote:
| I'll just add here that it doesn't have to be only one or
| the other. The ribbon might be good for discovering
| features, but it's inefficient for using those features
| once discovered. If the user already knows what the thing
| they want is called, the fastest way to find it is a search
| bar that searches the labyrinth of menus and ribbons when
| you type into it. Google and Mac apps usually have this.
| nanidin wrote:
| I think Apple's approach to menus is preferable - one can
| search and it will highlight places in the menu where the
| term appears. Usually I know what I want to do, I just
| don't know where it's located in the menu.
|
| For MS products I end up Googling how to do something and
| invariably get instructions for a slightly different
| version with a menu layout that is also slightly different
| and work it out from there.
| frosted-flakes wrote:
| MS Office has the same search behaviour, and the ribbon
| layout has not changed since it was first implemented in
| Office 2007.
| nanidin wrote:
| MS Office search doesn't show me where in the menu the
| item I searched for is located - if I rely on the search,
| I haven't learned where the thing is in the menu.
| hulitu wrote:
| > it lays out all the options in front of them in a clearly
| organized hierarchy
|
| I don't know for who is this hierarchy clearly organized,
| but for me it is not. Yesterday i spent 10 minutes
| searching on how to recall a mail in outlook. Searching for
| "headers and footers" is the same.
| nipponese wrote:
| Depends on the need. If they need someone to further explain a
| specific concept from their homework, they definitely know what
| they want.
|
| Also, if they just want a refund on an airline ticket, again,
| they know.
| haswell wrote:
| In the context of my comment, knowing what they want was more
| about users being able to tell me what they think they should
| do next in the software's interface (whether that's a GUI,
| terminal, or bot) to achieve their desired goal.
|
| In other words, what should we build as a product team to
| satisfy this user's need?
|
| The thing they need in the moment is often not obvious or
| apparent to them until they see it. This is why we iterate on
| UI concepts. Some work, some don't. Most of the things that
| work don't come from users who tell us "put this button
| here".
|
| So the point I was making was more about trying to determine:
| "what are the things I can even ask the computer?".
|
| There are clearly use cases that are better suited for this
| than others. Anything that follows a simple question/answer
| format is probably a great fit.
| tbihl wrote:
| >Asking a user to interact with one of these chat interfaces is
| like asking them what they want - every time they use the
| software.
|
| Asking what a user wants would be having a competent customer
| service representative, and would be simple, like asking me to
| drive home from work.
|
| Voice prompts require me to intuit the customer support
| structure in order to guess where the path is to reach my
| category of issue. It's like asking me to walk home from work
| in the sewer system.
| haswell wrote:
| For use cases that are well-suited to a conversational
| interface, that's great, and new AI advances will make
| chatbots more powerful than they've ever been.
|
| But not every use case is a chatbot use case, and I think
| that's the key point of the article.
|
| The sudden viability of a conversational interface that is
| good enough at having a fluid conversation to revolutionize
| the experience of that conversation does not suddenly make
| this interface the best fit for all use cases.
|
| I still find it far more pleasant to browse to a page and see
| a list of clearly displayed options that I can absorb at a
| glance and get on to what I really need to accomplish in the
| moment.
|
| Even a perfect conversationalist can't remove the extra
| friction involved in disclosing information. The question is
| whether that loss of efficiency is outweighed/nullified by a
| better overall experience.
| ghaff wrote:
| Even if someone designed an awesomely sophisticated air
| flight search engine that knew my usual preferences and
| could search for me and respond to follow-up prompts, I'd
| probably still want to see the information displayed on a
| page rather than read to me for the most part.
| haswell wrote:
| I think this might point to an opportunity to explore
| hybrid interfaces that allow you to just have a
| conversation while still having a visual representation
| of everything going on.
|
| But still agree with the sentiment here. There are
| applications that I cannot imagine ever wanting to
| interact with via a bot.
| dshah wrote:
| This is how I've been thinking about it.
|
| Hybrid interfaces that combine visual cues and output and
| natural language input.
| ghaff wrote:
| That's what I had in mind. Happy to talk to the computer
| but show me the results on a screen. If I'm typing in a
| freeform query, I'd generally just as soon say it
| instead. (Assuming I'm somewhere I can talk.)
| layer8 wrote:
| > like asking them what they want - every time they use the
| software.
|
| That reminds me of https://en.wikipedia.org/wiki/Where_do_you_w
| ant_to_go_today%..., which apparently wasn't successful.
| IanCal wrote:
| A chat interface is much more tolerant of this, because it
| implies a back and forth with clarification. Current one step
| dumb voice interfaces are a problem.
| haswell wrote:
| I interpreted the article to be calling attention to the
| situations when the tolerance of a chat interface is
| outweighed by a more efficient mode of information discovery
| that might be better suited to a specific use case.
|
| In other words, if you're building a new product, don't just
| slap a chat interface on it because AI is good now.
|
| This is not a claim that chat is never the right option.
| kilgnad wrote:
| Yes. This ^. ChatGPT is especially good at evolving and
| revising the main idea through a full on conversation. It is
| not just a query and answer machine. It is a full on
| conversational intelligence. Parent is incorrect. chatGPT is
| literally perfect for what he is describing.
|
| I feel people are attacking the things chatGPT excels at out
| of fear. Things like creativity, originality, true
| understanding of what's going on. chatGPT is GOOD at these
| things but people try to attack it.
|
| The main problems with chatGPT are truthfulness, honesty,
| accuracy and consistency. It gets shit wrong but out of fear
| people need to attack all aspects of chatGPT's intelligence.
|
| I find it unlikely the parent even tried to have a
| conversation with chatGPT about a product at all. A lot of
| our dismissals are largely surface level and not evidence
| based. You can bounce thoughts and product ideas off this
| thing and it will run with you all the way into a parallel
| universe if you ask it to.
| haswell wrote:
| I am not attacking chatGPT and I'm excited about what this
| tech will unlock.
|
| My point is that chat is not an appropriate interface for
| many use cases. Not knowing what I want in the moment as a
| user doesn't automatically mean I want to figure out what I
| want by having a textual conversation. There are times when
| I value and prioritize speed of discovery over a perfectly
| intuitive conversation that leads me there.
|
| For use cases that work well with chat, the future looks
| very bright.
| kilgnad wrote:
| Understood. I'm saying that talking about a product and
| bouncing product ideas off of chatGPT and asking for
| variations and creative additions to the product is
| something this AI is actually good at and it is very
| helpful with.
|
| But yes, I understand that many times you just want an
| exact answer quickly.
| the_af wrote:
| > _Things like creativity, originality, true understanding
| of what 's going on. chatGPT is GOOD at these things but
| people try to attack it._
|
| In what sense do you think ChatGPT is good at any of those?
| It seems evident to me it has no understanding, in the
| sense that it doesn't build a mental model of your
| conversation. Try playing tic tac toe with it: it will
| conduct a seemingly "good" game of it, until you notice it
| does wrong moves or "forgets" previous positions, or
| forgets whose turn is it to play. And if you correct it, it
| will fix the latest error but often introduce new ones.
|
| Someone who "understands" the rules of the game wouldn't
| make those mistakes repeatedly. And that's for a trivial
| game, imagine something more convoluted!
|
| And let's not start with "creativity" ;)
| kilgnad wrote:
| Take a look at this:
|
| https://www.engraved.blog/building-a-virtual-machine-
| inside/
|
| It's mindblowing. Read it to the end all the way to the
| mindblowing ending.
|
| I cannot for the life of me understand how someone can
| read the above and think chatGPT doesn't understand
| what's going on. Literally. There is no way this is just
| some statistical words jumble phenomenon.
|
| A lot of people are in denial EVEN when I show them that
| amazing article. What some people end up doing is trying
| the task in the article themselves then nitpicking at
| things chatGPT ends up lying about or getting wrong. Yes
| it does all of this. It's stupid in many ways but this
| much is true:
|
| That article showed that chatGPT understands what a linux
| bash shell is, it understands what the internet is, and
| it understands SELF. What do you call it when something
| understands SELF? Self awareness.
|
| Now i know that's a big word with big connotations. I
| think movies have kind of exaggerated the gravity of the
| word a bit too much. In movies, self awareness is skynet
| taking over the world, in reality self awareness is a
| simple trivial thing where some AI just understands
| itself in the context of the real world.
|
| Make no mistake. chatGPT is in many instances a stupid
| and dishonest machine, this is a fact. But it ALSO
| understands you and it ALSO has a very trivial self
| awareness. That article is very compelling evidence for
| this fact.
|
| As for creativity, I mean the fact that it can come up
| with original children stories is the definition of
| creative. At most what you can say is the creativity
| chatGPT posesses is generic and unoriginal (but even this
| can be circumvented if you push chatGPT enough) but you
| cannot deny it is creative.
| dmix wrote:
| Your analogy is building software though which is an extremely
| complicated, domain-filled specialization. I don't think people
| are suggesting user will be asking a chatbot to do crazy hard
| stuff like translate their complicated business problems into
| software interfaces (at least not yet).
|
| The usecases for AI/Chatbots will likely remain niche but
| there's still tons of niche areas a lanugage interface could
| fill, where the user has the appropriate specialization/skill
| to do it on their own.
|
| It is still ultimately an interesting design/UX question. It's
| too bad the OP blog post didn't provide some real life
| examples.
| haswell wrote:
| The point was less to draw an analogy and more to reflect on
| how I've seen users behave when exploring software for the
| first time.
|
| When testing new concepts, observing users try things out
| reveals a spectrum of expectations about where things should
| be, and how to achieve a task. So we try to find the
| combination of things that surprises people the least, as
| much of the time as possible.
|
| And when a new user doesn't find the chosen approach
| perfectly intuitive, this is usually a temporary problem,
| because learning where something is takes care of this with a
| few repetitions. Product tours help.
|
| An equivalent chat interface might be able to adapt on the
| fly to a wide range of user types, but this still doesn't
| imply anything about the core usability of the product and
| whether or not someone prefers to interact with a chatbot.
| Put another way, some use cases just aren't a good fit for a
| chatbot, even a very very good one.
|
| I do agree that though niche, there are a lot of interesting
| opportunities with a sufficiently fluent conversational AI.
| fragmede wrote:
| > users absolutely do not know what they want in the moment.
|
| People know what they want in a general sense. They need to be
| told they need _your_ one though.
|
| I need new clothes, but I don't know that I specifically wanted
| a black Nike T-shirt made of special exercise polyester until I
| saw the model in the ad wearing one.
| haswell wrote:
| I think this is a very different concept than the state of
| mind someone is in when trying to understand how a piece of
| software works.
|
| This obviously depends on the type of software, but users
| often struggle to articulate the actual problem they're
| trying to solve, and it's difficult to know what solution to
| look for when you haven't fully grasped the problem yet.
|
| If I don't know what the solution looks like, I don't know
| what to look for, and this is where good software steps in
| and _shows_ the user what to do next without making that an
| onerous process in perpetuity.
| jgautsch wrote:
| Some users do, and they're right. Talk to those ones often,
| it's much faster than the full build/measure/learn ceremony.
| haswell wrote:
| Oh absolutely. Those users are what made the job rewarding.
| Learning from them was invaluable.
|
| They're also rare, at least in the specific domain I was
| focused on.
| nanidin wrote:
| This resonates with me and my use of Siri. As soon as I get
| outside of the common tasks I use it for (setting timers, unit
| conversions in the kitchen, turn on/off the lights), I'm either
| spending time trying to come up with the correct incantation or
| pulling out my phone to get to an app that does it better.
| ddmma wrote:
| Adding machines into the way humans interact not only will make
| the experience more natural and enjoyable but definitely
| understand the environment both sides.
|
| I would celebrate the historic advancement of the technology
| instead of looking for flaws necessarily.
| pottspotts wrote:
| I've largely used GPT as a replacement for Google, and I find it
| to be a lot smarter and faster. The criticisms the author level
| at it don't seem based on having used it for anything
| substantial.
|
| It is an excellent tool and a major step, and it will only get
| better and easier to use, it seems.
| LASR wrote:
| 100% Agree.
|
| When it comes to SeriousBusiness(tm), chat bots don't have
| sufficient constraints to extract specific input from free-form
| text.
|
| Applications are ultimately delivering value in a specific set of
| use-cases. Only some of those use-cases can be easily retrofitted
| with a chat-first interface.
|
| Consider something like Photoshop or Figma. There are so many
| ways you can issue commands that don't make sense. Eg: "Change
| the font-size on this color palette."
|
| Any sophisticated app will have these kinds of constraints.
|
| The user interface is not there only to accept input from the
| user. It also implicitly teaches the user some of the constraints
| in their apps.
|
| Without that, you're shifting the burden of understanding and
| maintaining the constraints to the user. And you're left with a
| (much smarter version) of "Hey Siri, do xyz...".
|
| This is a common ideation trap I see with PMs at the moment. The
| underlying problem again is that the human doesn't understand the
| limits of what their apps can do for them. As a second order,
| even if they did, humans can be bad at describing what they want
| to do.
| intrasight wrote:
| Natural language is at least 100,000 years old. It's not lazy -
| it's just natural.
| dathinab wrote:
| lazy sure, but it's also the least precise by far
|
| tbh. the hardest part of many software projects is figuring out
| what really is needed
|
| I have seen startups with good tech and people fail because they
| slightly misjudged what their customers want and noticed way to
| late.
|
| A common cost driving factor when hiring a company to do a
| software project for you is that the requirements you legally
| agree one are not quite what you need so you have to pay for
| follow up changes. (This is also AFIK sometimes abused, initially
| underbidding the competition then "accidentally" creating a
| product which fits the requirements but not the actual needs and
| then selling overpriced follow up changes to an end code much
| higher then the competition would have been.)
| freedude wrote:
| All user interfaces should be as challenging as Perl RegEx. Here
| is a great idea; for the answer to be valid make it required to
| be in the form of a Perl RegEx. That will get rid of the lazy
| people.
| hulitu wrote:
| I think you never used a Microsoft GUI. PERL RegEx is
| deterministic.
| chinchilla2020 wrote:
| The worst online MUD I ever played had a tutorial puzzle that was
| something like this.
|
| "Now, use the mechanisms on the catapult to launch the catapult"
|
| There was no other explanation of what your options were.
|
| I tried: 'pull the lever' 'release the spring' 'fire the
| catapult' 'pull back the lever' 'use the lever'
|
| It finally turned out to be something like "release the lever".
|
| The problem with chat is that you are attaching it to a rigid
| user interface that has a tiny subset of options compared to the
| breadth of human language. The user has to probe the awful
| chatbot for these options.
| jasonjmcghee wrote:
| I agree that a singular text interface is far from an ideal ux, I
| do firmly believe providing smarter, more flexible command
| palettes will be a huge value-add to many user interfaces. Should
| you be able to interact manually - sure! But complex user
| interfaces tend to struggle with information architecture
| throughout their lifetime. Many of the obstacles could be well-
| mitigated by providing a declarative user experience - the
| easiest example is Jetbrains "Actions" interface.
|
| I wrote about my perspective in longer form a handful of months
| ago: https://productiveadventures.substack.com/p/the-rise-of-
| decl...
| rednerrus wrote:
| I've had GPT-3 as a replacement to Siri on my Apple Watch for the
| last month or so and it's awesome.
| monkpit wrote:
| How?
| rednerrus wrote:
| https://www.icloud.com/shortcuts/62624b2613b245698d81ebd9ac9.
| ..
| diogopublio wrote:
| here is a good example of a rudimentar use: multion.ai
| ed wrote:
| Cool! Looks like an improved version of Natbot
| https://github.com/nat/natbot
| diogopublio wrote:
| great to see an open source version, tks!
| janalsncm wrote:
| I still think voice should be the goal. It has been the universal
| API for thousands of years. All of us are probably "good with
| computers" by virtue of the fact that we figured out how to sign
| up but there are millions who aren't.
|
| This isn't an excuse to replace UIs or humans with horrible phone
| trees. I won't defend the obvious race to the bottom. Hopefully
| better voice interfaces are here soon.
| Barrin92 wrote:
| given the extent to which audio phone calls have been replaced
| by text I'm always super sceptical of voice as the primary
| interface.
|
| It has so many disadvantages. No simple to see history, loud
| (by definition) in any non-private space, not composable, not
| easily copyable, very slow discovery, and so on. Voice is
| strictly serial. Tactile or visual interfaces you can just look
| at and move around in and immediately have a layout of the
| thing.
|
| Regardless of how smart the voice control is those issues are
| pretty intrinstic. There's also no 'halting state' to voice.
| That you can switch between different visual interfaces without
| losing your state is pretty necessary today. But you can't
| really stop or multitask audio controls sensibly.
| jermaustin1 wrote:
| I can't help but agree fully. Its worse on telephones where they
| might be doing NLP, but they cannot understand and parse accents
| and dialects. I remember my late grandmother trying to call AT&T
| a couple of years ago (just before COVID), and the robot would
| ask: "What can I help you with?" and then could not understand
| how she pronounced "pay my bill" because she said "PAY mah
| BEEEEEL".
|
| But just hitting 0 did nothing, so after 5 minutes of her
| repeating "PAY mah BEEEEL" over and over, I took the phone from
| her and did it. From then on she would have to have other people
| pay her bill over the phone.
|
| Doing this to a much more complex user interface and providing me
| no clue what I'm supposed to ask for something I have no way of
| knowing that I don't know it is a dystopian future I'm glad my
| grandmother won't have to endure.
| hacker_9 wrote:
| It's poor thinking on them to _only_ provide a talking
| interface. I don 't think I've encountered that personally,
| there is always a way to use the keypad - which I will always
| use anyway, even though they understand my voice, it's just x10
| faster. And if you've made the call before you can type on the
| keypad before the robot on the other side is done talking.
| tiagod wrote:
| There's plenty of services in Portugal that only have the
| damned robots. They're also adding the most infuriating
| chatbots that they pretty much force you to go through before
| getting to a human. Can't wait for the day this is all
| banned.
| Dudeman112 wrote:
| Whenever this is discussed, it always makes me wonder...
| Why? Just why?
|
| SURELY just adding an option to use the damn textual "pick
| 1 for Blah, 2 for bleh..." would take no effort at all?
| monkpit wrote:
| You also have to consider - does the company you are
| calling BENEFIT from you hanging up in anger/frustration?
| Many times the answer is yes.
| Dudeman112 wrote:
| Most of the time the answer long term is "no" because as
| long as it's not a monopoly people will go to their
| competitors that aren't utter shite at what they do
| monkpit wrote:
| I think the number of people who would actually do this
| is smaller than you think.
| passwordoops wrote:
| I don't have data but more and more seem to be turning voice
| only. Some US-based airlines come to mind, and one of the
| banks I deal with. It's fun when they ask for my "16 to 20
| digit client number"
| Pxtl wrote:
| And then they spend half a minute slowly reading back each
| digit to ask "is this correct?"
| wrycoder wrote:
| Mine just started introducing an ad before they get to
| the main menu.
|
| Also, they repeat things several times during the
| interaction. i.e. the phone number I just called.
|
| "Do you want to repeat that or go to the main menu?"
|
| "Main menu."
|
| "You want to go to the main menu, is that right?"
|
| It's not my pronunciation, it does that _every_ time.
|
| Bot time is considered cheap, and therefore so is the
| user's time. The time for the transaction has doubled
| over the last five years, as they add more repeats,
| information, and now, ads.
| [deleted]
| passwordoops wrote:
| As a 40-something white male with a neutral, Urban Canadian
| English accent (so the ideal NLP user), even I have difficulty
| with voice assistants and ABHOR being forced to use one. My
| wife does have an accent and like your late grandmother always
| has great difficulty with these, usually requiring my
| intervention.
|
| Unfortunately, NLP is "modern" and "eliminates drag" according
| to current design-think. What's needed is a shift from thinking
| about "User Experience" to the real lived human experience when
| designing interfaces
| chinchilla2020 wrote:
| That's the issue. The academic and research UI/UX spaces tend
| to reject user feedback. The explanation is that "You must
| train the users to like it".
|
| Deeply unpopular changes that are gaining traction in
| industry but hated by users are: 1. removal of all buttons
| from devices in favor of screens 2. voice bots and text bots
| 3. gesture interfaces
| marcosdumay wrote:
| > The academic and research UI/UX spaces tend to reject
| user feedback.
|
| I dunno. I am yet to see the academic and research UI/UX
| having any impact on the real world on this century.
|
| Everything you see around was created by somebody else.
|
| So, since I also have not been looking for their work, I
| have no idea what they are saying.
| Existenceblinks wrote:
| Agreed. I'm afraid to say that UX/UI buzz is overrated,
| it's 99% copy 1% mix and match. And there's no
| revolutionary ideas. To be fair, something is truly hard
| to the point I don't think there's a fix such as UI for
| tree data, it's all sucks given current 2d screen we
| have.
| yellowapple wrote:
| At the risk of some choir-preaching: if you have to train
| users to like your UX, then you have fundamentally failed
| at UX.
| passwordoops wrote:
| These are the same brain geniuses who parrot the old "Henry
| Ford said if asked, my customers would demand faster
| horses"
|
| Really? Aside from the fact the quote cannot be attributed
| to him, was this before or after he was forced out as CEO
| when bringing Ford to the brink of bankruptcy for, among
| other things, declining sales caused by not listening to
| clients? In the middle of the roaring 20s - you know that
| period of time when everyone was buying things like new
| cars? And companies like Chrysler boomed by provided
| features that clients wanted? Because they asked and
| listened. That Henry Ford?
| [deleted]
| hinkley wrote:
| Regional accents are terrible that way. Are you sure it was
| "BEEEEL"? There are places where "bill" is two syllables. I'm
| surprised you didn't get "PAY mah BEE ILL"
| imbnwa wrote:
| My grandfather speaks in a thick, archaic Northern Georgia
| brogue I can't imagine anything parsing his speech correctly
| since to the untrained ear it sounds like one long continuously
| occilating grumble sorta like Boomhauer from King of the Hill
| but deeper and with more bass. You can generally hear him
| pronounce "shit" pretty clearly though.
| [deleted]
| Thoreandan wrote:
| English was my mother's 5th language, I can relate to acting as
| interpreter for family.
|
| I'm reminded of the "Voice Recognition Lift" sketch from the
| Scottish comedy Burnistoun -
| https://www.youtube.com/watch?v=TqAu-DDlINs
| LouisSayers wrote:
| When I moved to London I went to the supermarket and asked in
| my New Zealand accent where the eggs are.
|
| "The what?" The assistant replied, "the eegs" I replied.
|
| "I don't think we sell those" he said.
|
| I switched to an American accent and he was finally able to
| understand.
| GrinningFool wrote:
| For future reference, when these systems offer you a choice of
| things to say like "Pay my bill", "Check my balance", etc, they
| are usually backed by numeric input too. You can press the
| number corresponding to the voice option provided - in this
| example 1) pay bill, 2) check balance.
| seydor wrote:
| LLMs can also talk, not just listen
| marcosdumay wrote:
| LLMs inherently do not know what questions to ask. Other
| algorithms know, but not them.
| ctoth wrote:
| Can't each and every one of these criticisms be also leveled at
| CLIs? Don't we like CLIs? I notice I am confused.
|
| > The least it could do is intelligently give me a starting point
| for typing in a prompt. The tyranny of the blank textbox is real.
|
| Seems LLMs would be way better at this sort of thing -- What can
| I do here, instead of "do I type help? man? apropos?"
| Pxtl wrote:
| While the discoverability of magic-word linguistic interfaces
| and command-lines do have some commonalities, my keyboard has
| never failed because it couldn't understand my accent.
| hunter2_ wrote:
| If we're comparing CLIs with text chat bots, accents affect
| neither. I don't think the concept of NLP generally implies
| voice more than text, and TFA specifically discusses
| textboxes.
| marcosdumay wrote:
| Hum... If your CLI doesn't have a manual, yes, that applies.
| hunter2_ wrote:
| I agree very much, but CLIs are mostly for power users and
| developers these days. Normal users were on CLIs decades ago
| but have been primarily on GUIs since then, for essentially the
| same reasons that TFA argues. I think we can focus on normal
| users for the purpose of this discussion.
| hulitu wrote:
| > Can't each and every one of these criticisms be also leveled
| at CLIs? Don't we like CLIs? I notice I am confused.
|
| It is not about text. In CLIs you have a set of commands. In
| those interfaces you have some hidden commands which you must
| trigger with keywords.
| hinkley wrote:
| Node and npm are notorious for having command line flags
| almost none of which are listed in the help, and less than
| half of which are documented on the website. I'm running node
| and npm flags in production deployment pipelines right now
| that I found on Stack Overflow or the bug database and exist
| nowhere on the official websites. And if you look at the
| historic documentation, the current situation is a factor of
| 3 improvement over even Node 10 or 12 era, which is far
| better than the node < 1.0 period
|
| What you say is true of _good_ CLIs, not tire fires like
| Node.js. So you 're both right depending on context.
| Existenceblinks wrote:
| Button is the goat user interface. Sound engineer devices, plane
| consoles, etc. I have the same thought since 2010, IIRC it was
| voice commands hype back then. I think they should focus on
| interfaceless learning model .. but I don't know what pure
| semantic they suppose to eat (learn) .. maybe TBs of XML lol.
| phs wrote:
| Would databases have been better to work with if SQL didn't ape
| natural language?
|
| Would Excel, if it _did_ choose to embrace a "natural" macro
| syntax?
|
| Remember when CGI movies were all stuck in the uncanny valley?
| Turns out language has a valley too.
| anotheryou wrote:
| It's versatility that's king here.
|
| Sure a knob for "snow flake size" is nice, but most often I don't
| work on snowflakes and their sizes.
|
| But if I do in the near future I'm sure I can just say: "I used
| snowflake size in a lot of my prompts, can you just make it a
| knob for me?"
| cwalv wrote:
| Spot on. Now word can augment it's UI, maybe automatically
| recognizing when I'm writing a letter and offering to help with
| that specific task.
| hulitu wrote:
| "Looks like you're writing a letter. Would you like help with
| that ?"
|
| The good old days, when the first thing you do after installing
| Office was disabling Office Assistant.
| aogaili wrote:
| That textbook saves many clicks and Google searchers, questions
| and running around. It is not lazy; it is just a more effective
| tool, and humanity is all about progressive tech.
|
| So it is not being lazy; it is being..human.
| mk_stjames wrote:
| This parallels a longstanding critique I have of many modern user
| interfaces compared to slightly older software in the field of
| what I would consider 'power user' engineering tools; programs
| like FE tools, CAD & other CAE, etc. These are the kind of
| programs that had a stride starting in the late 90's to 2007-ish
| where they just slammed tons of toolbars around the edges of the
| screen, sometimes nesting functions or contexting workbenches but
| ultimately allowing the user to have everything exposed to them
| at once if needed. As screen real estate grew with higher res and
| larger monitors, the icons got smaller which was even better for
| the power user- you could fit even more on the screen if you
| wanted!
|
| But starting around 2008-2009 I noticed a trend, and it continues
| to this day- the power user oriented layouts started being
| replaced with more 'friendly', larger icon, children's game
| looking UI. Intuitive graphical icons were replaced with stylish,
| monotone shit that looks like a graphic design student's dream,
| but conveyed less instant information.
|
| I blame some of this shift on the move in Office to the Ribbon
| system and developers trying to imitate that, but some software
| I've seen takes that and does it much worse.
|
| I want all my functions laid out and accessible. Like this blog
| post mentions, sometimes I don't know what I am wanting to do
| until I see it. I want to be able to explore the entire space
| before I know what it all does, maybe.
|
| Using natural language can be very powerful if it augments these
| systems, but for many tools it isn't a replacement. Often I think
| new software is designed around looking impressive and fast to
| upper level management at the expense of the usability of the
| power users who ultimately are the users that get things done.
| Def_Os wrote:
| Instead of the Ribbon, don't you think it was rise of tablets
| that influenced these design changes?
| klabb3 wrote:
| > Intuitive graphical icons were replaced with stylish,
| monotone shit that looks like a graphic design student's dream,
| but conveyed less instant information.
|
| Design is the art of signal-to-noise ratio, or in simpler
| terms, balance and harmony. If you over-use any modality,
| lines, text, color, nesting, you increase the noise level. If
| you underutilize a modality (for instance your whole UI is
| monochrome), you reduce your signal bandwidth.
|
| Every trend gets mindless followers, who throw the baby out
| with the bath water without even realizing it. But trends also
| bring a grain of gold to the table.
|
| For instance, monotone icons allow many more elements in the
| same screen real estate than text, and by not using color you
| can have a larger color budget for other elements, which you
| can use elsewhere to convey progress, status, or anything else
| important.
|
| A good use of monotone icons are text formatting (bold,
| justify, etc) and display options (column view, tree view,
| etc), or toolbars (like in photoshop or 3D tools). Many apps
| from the 2010 era overused colored icons, and I'm glad those
| went away. Some FOSS apps still suffer from that.
| kris_wayton wrote:
| I agree it's not for everything, but it seems like better NLP/NLG
| could improve things like Alexa a lot. Alexa is fine for setting
| timers, turning off lights, etc. But currently when I ask it
| anything that Google Search or ChatGPT handles well, Alexa falls
| down and tells me the wrong info.
| AstixAndBelix wrote:
| The reason terminal interfaces are often criticized is because
| they lack discoverability, leaving the user at a complete loss or
| at least hiding the full array of functions the program offers.
|
| The reason many amateur GUI programs (GIMP) are criticized is
| because they lack discoverability, leaving the user at a complete
| loss or at least hiding the full array of functions the program
| offers.
|
| The reason many programs based on NLMs will be criticized is
| because...
| hunter2_ wrote:
| Right: it turns out that when someone wants to offer someone
| else a plethora of options in one fell swoop, graphics are much
| more efficient than language because it takes way less time to
| consume. Even if commands like "help" or "what can I ask you
| about" end up providing equivalent discovery, consuming that
| delivery (whether reading text or listening to spoken word)
| takes many times longer.
|
| Users of screen readers mitigate this by cranking up the speed
| to levels that typical users would severely struggle to
| understand: it takes a lot of practice to get efficient with
| using language in this way efficiently.
|
| And chat bots often add artificial delay in an attempt to
| humanize the experience -- making this even worse!
| GrinningFool wrote:
| > graphics are much more efficient than language
|
| Graphics are just another language. When looked at across
| desktop applications, mobile applications, operating systems,
| and web sites it's a language that's much less consistent
| than any written language.
| soorya3 wrote:
| Chatbot may be lazy user interface for some tasks but it is very
| good at assistive task like writing, coding, review etc. It is a
| language model and a foundation for other software products. Over
| time integrating with LLM into existing user interfaces will
| solve the problem you mentioned.
| sigmonsays wrote:
| I wonder if there is something in rust that can be done to
| improve the LLM
| Existenceblinks wrote:
| You missed opportunity of LL[V]M
| davidkunz wrote:
| Chat interfaces are great if
|
| 1) you know what you want 2) the alternative would require manual
| navigation to multiple UIs and/or many interactions
| philip1209 wrote:
| Google's natural language interface seems to be popular.
| RyanShook wrote:
| Chat tools that help power users access features or settings
| inside of an app are where I think the immediate value is. App
| interfaces are super simple which reduces cognitive load on the
| user but hides many needed features. I have to hunt around so
| many app and website pages to find the setting I need and I think
| this is an area good chat interfaces can excel.
| sam_lowry_ wrote:
| Robert Sheckley said it way better in Ask a Foolish Question [1]:
|
| "In order to ask a question you must already know most of the
| answer."
|
| [1]
| https://www.gutenberg.org/cache/epub/33854/pg33854-images.ht...
| [deleted]
| pelorat wrote:
| > "people are bad at words"
|
| People are worse at command line interfaces and even clicking on
| buttons.
| corytheboyd wrote:
| Best of both worlds is a searchable action menu. Search matches
| action names as well as description, bonus points if it shows
| related actions as well. Actions have help documents if
| necessary. Solves the discovery problem, is still deterministic
| and sensible, doesn't need anything more fancy than full text
| search. Add ML if you have to, but for nothing more than a
| "suggested" list of actions, NOT as a replacement for
| deterministic search.
___________________________________________________________________
(page generated 2023-01-27 23:00 UTC)