[HN Gopher] What will LLM-powered software look like in the medi...
___________________________________________________________________
What will LLM-powered software look like in the medium-term future?
Author : vishnumenon
Score : 180 points
Date : 2023-09-18 18:25 UTC (2 days ago)
(HTM) web link (vishnumenon.com)
(TXT) w3m dump (vishnumenon.com)
| gnarcoregrizz wrote:
| > the "inefficiency" involved in carrying out many digital tasks
| "manually" is a core driver of the joy that comes with using
| computers (for me and, I assume, for at least some subset of
| others)
|
| A lot of people feel this way. The romanticism of computing is
| diminished by LLMs. Call me a luddite. I even work in AI.
| makestuff wrote:
| Clippy is going to make a triumphant return as the AI assistant
| of the future. Clippy will be on every phone/tablet/computer just
| talking to other instances of itself.
|
| In 5-10 more years models will all run locally on device with
| weight updates being pushed OTA.
|
| Advertisers will somehow figure out how to train ads into these
| models so you get subtle references to new products.
| ozten wrote:
| ... concludes your helpful outdoor activities this weekend.
| Also, try Lawn Darts, which the cool kids call "Jarts". (Sorry,
| training data was cut off in Jan 1970)
| jasfi wrote:
| LLM generated UIs sound interesting, but would likely ensure
| nightmarish bugs. But if it can be done, someone will try it.
|
| I might try it.
| isoprophlex wrote:
| Loving the ideas here. I'm especially fond of the machine-to-
| machine idea, the concept of a locally running LLM that knows
| about you, and a remote LLM in an app or whatever, interacting
| with eachother to create a highly individualized UX.
|
| Seems like a perfect blend of keeping the core personality of the
| LLM trained on your data local, while still allowing permissioned
| access.
| mstipetic wrote:
| I'm currently building something that touches on point 4, the
| dynamically generated UI. I'm building basically copilot for PMs
| that integrates with your project planning tool and so far it's
| been working like magic. You can literally tell it to output a
| json and use it like an API.
|
| I think my main jobs are getting the prompts right and building
| an UI and UX experience that makes sense, and the rest is somehow
| taken care of by magic.
| jumploops wrote:
| There is LLM-powered software and then there is software
| developed with the help of LLMs.
|
| These paths are not mutually exclusive, but I'm personally more
| excited about the latter.
| nathan_gold wrote:
| I can give a basic example of why chat-based UI will not
| dominate.
|
| Let's say I want to change a setting that uses a traditional
| radio button UI:
|
| - Autoscale servers - Manual scale servers
|
| It's much easier to discover, understand the options, and make a
| decision via a radio button UI than to ask for my options via
| chat. That would look like:
|
| "I'm having load issues on my servers. Can you increase the
| server capacity?" "Sure! Do you want to autoscale or manual
| scale?" "What's the difference? Are those the only two options or
| are there more?" "There are only these 2 options. The difference
| is..."
|
| That's just a worse UX.
| mpalmer wrote:
| But it's not either/or. There's nothing that says you can't
| have a visual interface that adjusts based on both natural
| language feedback and traditional cursor-based input.
|
| There are great examples of this in Westworld and The Expanse,
| with characters talking to screens to update and refine their
| queries.
| bbarnett wrote:
| _That 's just a worse UX._
|
| So are touchscreens, especially in cars. Physical buttons are
| far better for the end user.
|
| Imagine a future when all people know is blah blah to use
| computers, can't type, never see buttons, and barely read any
| more.
|
| Now is it a bad UX?
|
| (Before the Internet, the majority of people rarely read. And
| even now, most people don't read, they tiktok, they youtube.)
| predictand wrote:
| I agree with the author that chat interfaces for LLMs can be
| suboptimal. A chat could require redundancies that is not
| required to perform a task and it imposes a linear flow of
| information. It is hard to have branching behaviour in a chat. I
| have been experimenting with using a different kind of a UI to
| overcome these limitations: https://www.heuristi.ca/
| freckletonj wrote:
| In answer to the same question I built UniteAI
| https://github.com/freckletonj/uniteai
|
| It's local first, and ties many different AIs into one text
| editor, any arbitrary text editor in fact.
|
| It does speech recognition, which isn't useful for writing code,
| but is useful for generating natural language LLM prompts and
| comments.
|
| It does CodeLlama (and any HuggingFace-based language model)
|
| It does ChatGPT
|
| It does Retrieval Augmented Gen, which is where you have a query
| that searches through eg PDFs, Youtube transcripts, code bases,
| HTML, local or online files, Arxiv papers, etc. It then surfaces
| passages relevant to your query, that you can then further use in
| conjunction with an LLM.
|
| I don't know how mainstream LLM-powered software looks, but for
| devs, I love this format of tying in the best models as they're
| released into one central repo where they can all play off each
| others' strengths.
| ryanjshaw wrote:
| > I don't believe that natural language is an adequate medium for
| conveying instructions with the precision required for many
| applications.
|
| Not clear to me if the author actually uses LLMs to do meaningful
| work, or is speculating about how they might be used.
|
| I've written about 2500 lines of F# for the first time in the
| past 1.5 weeks using ChatGPT-4 to guide me. It has been an
| constant back and forth, iterative process. My decades of
| development experience factored in heavily to guide the process.
| I would've have been at maybe a quarter the progress without
| ChatGPT, or given up entirely on F# as my language.
|
| I don't think that iterative aspect will be eliminated any time
| soon for AI-supported complex, creative processes. It's no
| different from tweaking inputs to a Photoshop filter until your
| experienced brain decides things look right.
|
| To that end you need to know roughly what looks "right" before
| you use an LLM. This will all become second nature to the average
| developer in the next 5-10 years.
| waynesonfire wrote:
| I had similar success when trying to solve problems with
| Makefiles.
| sanderjd wrote:
| Yeah, for me it has been docker and kubernetes. I have found
| it to be something of a killer app for spinning up on
| anything with a bunch of annoying little details, that I'm
| not already super familiar with.
|
| Make, docker, kubernetes, all fit this pattern. Heck, maybe I
| won't be so down on autotools if I run into it again now that
| I can attack it with LLM support.
|
| Or html / css; I haven't written any of that in the LLM era,
| but maybe I'd enjoy it more now.
| vishnumenon wrote:
| I'm the author, and I don't disagree with this at all - I do
| use LLMs pretty meaningfully in my day-to-day engineering work,
| and I definitely agree that they hold a ton of promise in
| situations like the one you mentioned. To be clear, I'm very
| much bullish on the applications of LLMs to e.g. coding! The
| point I was trying to make there was just that for _certain_
| tasks, the process of chatting with an LLM is, by nature, less
| precise and more arduous than a purpose-built UX. By analogy,
| we might have "describe-your-change" functionality in
| Photoshop, but its no replacement for all the other pixel-
| perfect editing functionality that it provides, and I'd
| struggle to imagine a world where Photoshop is ever _replaced
| entirely_ by a chat UX
| kristianp wrote:
| The llm effect may enable people to use languages that are
| harder to write, but produce a more maintainable and/or
| performant product. Maybe it's finally time to learn rust or
| ocaml!
| lysecret wrote:
| Ah haha I am going through the exact same experience but picked
| up F# about 4 months ago and ChatGpt has been an absolute
| godsend. There is a whole category of blockers in learning that
| have been eliminated.
| depletedgherkin wrote:
| Bit of an aside, but I wonder if the rise of LLMs will lead to
| new programming languages being much slower to be adopted.
|
| Like you said, you might have given up on F# without ChatGPT
| assistance, and the main way ChatGPT is able to help with F# is
| because of all of the example code it's been trained on. If
| developers rely more and more on LLM aid, then a new language
| without strong LLM support might be a dealbreaker to widespread
| adoption. They'll only have enough data once enough hobbyists
| have published a lot of open-source code using the language.
|
| On the other hand, this could also leading to slowing adoption
| of new frontend frameworks, which could be a plus, since a lot
| of people don't like how fast-moving that field can be.
| bostonsre wrote:
| Wouldn't you just need to publish a Rosetta stone type
| translation for it to be able to digest the new language
| fully? e.g. here is how you do this in python and here is how
| you do it in this new language
| Closi wrote:
| I've also wondered this - including if we might see a breed
| of 'higher level' languages (i.e. much higher level than
| Python) which can then be 'AI compiled' into highly efficient
| low level code.
|
| i.e. the advantages of an even-higher-level python that's
| almost like pseudo-code with assembly-level speed and rust-
| level safety, where some complexity can be abstracted out to
| the LLM.
| waynesonfire wrote:
| I disagree. Chatgpt is helpful here because f# is a
| paradigm shift for this otherwise experienced programmer.
| The programmer probably knows juuussstt enough f# to guide
| the llm.
| Closi wrote:
| I mean why is f# the goal, and could we write a better f#
| with the use of AI.
|
| As an example, why not write in f# and let an 'AI-
| compiler' optimise the code...
|
| The AI-compiler could then make sure all the code is type
| safe, add in manual memory management to avoid the
| pitfalls of garbage collection, add memory safety etc -
| all the hard bits.
|
| And then if we gave the AI-compiler those sort of
| responsibilities, then we can think about how this would
| impact language design in the longer term.
|
| None of this is with current generation LLM's, but might
| be where we end up.
| jprete wrote:
| This doesn't require AI, it requires higher-level
| languages than we have that can express intent more
| directly.
| Closi wrote:
| In current generation language there is definitely a
| trade-off between language productivity (i.e. speed of
| writing) and features such as speed and memory-safety.
|
| So far we haven't been able to close this gap fully with
| current compilers and interpreters (i.e. python still
| runs slower than C).
|
| It seems like that gap could be closed through, for
| example, automated refactoring into a rust-like language
| during compilation, or directly into more-efficient byte-
| code/ASM that behaves identically.
|
| And surely if that is a possibility, that would affect
| language design (e.g. if you can abstract away some
| complexity around things like memory management).
| [deleted]
| throwuwu wrote:
| The crazy thing that a lot of people don't realize is that
| all of that data generalizes to anything new you can throw at
| it. As long as there's enough space in the prompt to provide
| documentation it can do it on the fly but you could also fine
| tune the model on the new info.
| Spivak wrote:
| Which is what Phind tries (and mostly succeeds) in doing.
| LLM + Search Engine is way smarter than just LLM.
| yayitswei wrote:
| I heard somewhere that ChatGPT is surprisingly good for human
| language translations even though it's not specifically
| trained for it. There seems to be just enough examples of
| e.g. Japanese that Japanese researchers use it to translate
| papers. I suspect that's largely true for programming
| languages too. I've had great success working with it in
| Clojure, even though there's relatively little published code
| compared to more popular languages.
| bugglebeetle wrote:
| ChatGPT is pretty good for translations of Japanese into
| English. It's English to Japanese translation tend to sound
| somewhat stiff/formal/machine-generated, although it's less
| prone to hallucinations than DeepL for larger texts. I
| expect this is because it was trained on a much larger
| corpus of English language texts than Japanese ones, which
| means the problem is not intractable.
| Buttons840 wrote:
| It could go the other way. LLMs might make porting code from
| one language to another easier which would speed the adoption
| of newer and more niche languages. And the future of
| documentation and tutorials might be fine-tuning an LLM.
| gumballindie wrote:
| To this day i am still wondering what kind of code people write
| that chatgpt can possibly help with. All my attempts lead to
| garbage and i would spend more time fixing the output of the
| chat bot than writing the actual code. It does help with some
| documentation. But even that has glitches.
| mk_chan wrote:
| I used chatgpt4 to generate python code which generates c++
| code for a hobby project of mine using a library I've never
| used before. The iteration speed is ridiculously good and no
| one in any of the IRC or discord channels I visited pointed
| me even in the general direction of such a simple solution.
|
| https://chat.openai.com/share/d041af60-b980-4972-ba62-3d41e0.
| .. https://github.com/Mk-
| Chan/gw2combat/blob/master/generate_co...
| bostonsre wrote:
| If you are trying to do something with an api that you have
| no experience with it will get you up and running quickly.
| e.g. How do I get all kubernetes configmaps in a given
| namespace older than n days in go? It gives you the bones
| about how you create and configure a client and query
| kubernetes to get the information that you are looking for.
| It's much quicker than googling and parsing a tutorial.
| [deleted]
| havnagiggle wrote:
| It's what Clippy always wanted to be.
| j-a-a-p wrote:
| Did some ETL with Python. ChatGTP got it right 99%. And,
| remarkably understood a public API that I was feeding from,
| which used 2-letter abbreviations.
| timacles wrote:
| It's good at a beginner, early intermediate level when you
| need help with syntax and structuring basic things. It's an
| excellent helper tool at that stage.
|
| But it's obvious outside of jr dev work and hobby projects
| there's no way it could possibly grasp enough context to be
| useful.
| kyleyeats wrote:
| Stage? A lot of developers don't realize that they're all
| the same personality type which is good at particular
| things. LLMs give everyone else this advantage. You just
| don't realize it yet because you were never aware of the
| advantage in the first place.
| timacles wrote:
| I'm not really following what you're trying to say. What
| is that personality type, and what are the things its
| good at? What is the LLM advantage?
|
| Not saying your post is devoid of any substance, just
| trying to educate myself on my blindspots
| kyleyeats wrote:
| There are three types of intelligence: intuitive,
| cognitive and narrative.
|
| Tech has, for years, seen people with cognitive/narrative
| intelligence as the people who are actually smart.
|
| LLMs help the intuitive people reach the level of the
| cognitive/narrative people. Cognitive/narrative people
| can't really understand this in the same way the
| intuitive people are bad at syntax or database structure.
| The steamrolling will be slow and merciless.
| [deleted]
| AlexCoventry wrote:
| Could you give a concrete example of where ChatGPT is
| likely to provide a competitive advantage to intuitive
| people with weak cognitive/narrative capabilities?
| gumballindie wrote:
| > they're all the same personality
|
| Yeah usually it was the shittiest managers I ever met
| that shared this belief. It sounds like they all repeat
| the same thing - gpt is a better google.
| kyleyeats wrote:
| Are you calling me a shitty manager? Would you say this
| to my face? What's wrong with you?
| gumballindie wrote:
| I am not, but there's a tendency among those types that
| categorise people into narrow sets that they can
| understand. Also your statement doesn't much make sense.
| Being a good developer means you understand a wide range
| of issues, not just spelling in a language and adding if
| statements. The combination of personalities vary wildly.
| To be fair, LLMs if anything, will help developers become
| better managers, simply because developers understand
| what needs to be done. Instead of decyphering what
| someone meant by requesting a vague feature, you can ask
| a statistical system - an ai as some call it - what the
| average joe wants. And then get it done.
| 6510 wrote:
| Treat it like your rubber duck.
| wokwokwok wrote:
| No one uses it to generate code. Really. Talk to people who
| actually use it and listen to what they say... they use it to
| help _them_ write code.
|
| If you try to generate code, you'll find it underwhelming,
| and frankly, quite rubbish.
|
| However, if you want an example of what I've seen multiple
| people do:
|
| 1) open your code in window a
|
| 2) open chatgpt in window b (side by side)
|
| 3) _you_ write code.
|
| 4) when you get stuck, have a question, need advice, need to
| resolve an error, ask chatgpt instead of searching and
| finding a stack overflow answer (or whatever).
|
| You'll find that it's better at answering easy questions,
| translating from x to y, giving high level advice (eg. Code
| structure, high level steps) and suggesting solutions to
| errors. It can generally make trivial code snippets like "how
| do I map x to y" or "how do I find this as a regex in xxx".
|
| If this looks a lot like the sort of question someone
| learning a new language might ask, you'd be right. That's
| where a lot of people are finding a lot of value in it.
|
| I used this approach to learn kotlin and write an IntelliJ
| plugin.
|
| ...
|
| ...but, until there's another breakthrough (eg. Latent
| diffusion for text models?) you're probably going to get
| limited value from chatgpt unless you're asking easy
| questions, or working in a higher level framework. Copy
| pasting into the text box will give you results that are
| exactly as you've experienced.
|
| (High level framework, for example, chain of thought, code
| validation, n-shot code generation and tests / metrics to
| pick the best generated code. It's not that you _cant_
| generate complex code, but naively pasting into
| chat.openai.com will not, ever, do it)
| tyingq wrote:
| That matches my experience. It's a sort of shortcut to the
| old process of googling for examples and sifting through
| the results. And those results, I didn't typically cut and
| paste from them, or if I did, it was mostly as a sort of a
| scaffold to build from, including deleting a fair amount of
| what was there.
|
| Many times it works really well, and it surfaces the kind
| of example I need. Sometimes it works badly. Usually when
| it's bad, going to the google/sift method has similar
| results. Which I guess makes sense, it couldn't find much
| to train on, so that's why it's answer wasn't great.
|
| One area it works really well for me is 3rd party apis
| where their documentation is mostly just
| class/function/etc. ChatGPT generally does a good job of
| producing an orchestrated example with relevant comments
| that helps me see the bigger picture.
| shanusmagnus wrote:
| Me too. As someone who used to be a dev but hasn't
| written code professionally in twelve years or so, it was
| such an amazing accelerant. My iteration loop was to
| contextualize it (in English and in code), ask how to do
| a thing, look at its response, tweak it, execute, see
| what happened, alter it some more.
|
| The fact that it usually had errors didn't bother me at
| all -- it got much of the way there, and it did so by
| doing the stuff that is slowest and most boring for me:
| finding the right libraries / functions / API set up,
| structuring the code within the broader sweep.
|
| Interesting side note: un-popular languages, but ones
| that have been around for a long time and have a lot of
| high-quality and well-documented code / discussion /
| projects around, are surprisingly fecund. Like, it was
| surprisingly good at elisp, given how fringe that is.
| bumbledraven wrote:
| With GPT-4, you can often just paste the error message in
| without any further commentary, and it will reply with a
| modified version of the code that it thinks will fix the
| error.
| gumballindie wrote:
| And then you waste time fixing the error the "fix" gpt
| introduced. Clever.
| ryanjshaw wrote:
| I've used it on this side project for:
|
| - A rough crash course in F#. I'll say "what's the equivalent
| in F# of this C# concept?". It will often explain that there
| is no direct concept, and give me a number of alternative
| approaches to use. I'll explain why I'm asking, and it'll
| walk through the pros/cons of each option.
|
| - Translating about 800 lines of TypeScript JSON schema
| structures to F#. A 1:1 translation is not possible since
| TypeScript has some features F# doesn't, so ChatGPT also
| helped me understand the different options available to me
| for handling that.
|
| - Translating psuedo-code/algorithms into idiomatic F# as a
| complete F# beginner. The algorithms involve regex + AST-
| based code analysis and pattern matching. This is a very
| iterative process, and usually I ask for one step at a time
| and make sure that step works before I move onto the next.
|
| - Planning design at a high-level and confirming whether I've
| thought through all the options carefully enough.
|
| - Adding small features or modifications to working code: I
| present part of the function plus relevant type definitions,
| and ask it for a particular change. This is especially useful
| when I'm tired - even though I could probably figure it out
| myself, it's easier to ask the bot.
|
| - Understanding F# compiler errors, which are particularly
| verbose and confusing when you're new to the language. I
| present the relevant section of code and the compiler error
| and 90% of the time it tells me exactly what the problem and
| solution is; 5% of the time we figure it out iteratively. The
| last 5% tends I have to stumble through myself.
|
| - Confirming whether my F# code is idiomatic and conforming
| to F# style.
|
| - Yes it makes mistakes. Just like humans. You need to go
| back and forth a bit. You need to know what you're doing and
| what you want to achieve; it's a tool, not magic.
|
| Note: this is the commercial product, ChatGPT-4. If you're
| using the free ChatGPT 3.5, you will not be anywhere near as
| productive.
| [deleted]
| kopos wrote:
| I've have used ChatGPT for
|
| - De-obfuscate a obfuscated JS code
|
| - Unminify a JS code. Asked it to guess function names based
| on the functionality
|
| - Work with it like a rubber duck to plan out the possible
| solutions to a code problem
|
| - To suggest function names based on the functionality
|
| - To name repos
|
| - Modify a piece of Go code to add specific functionality to
| it. I don't know to write Go; I can read it and grok the high
| level functionality
| kelseyfrog wrote:
| Programmers[1] have a complexity bias that interferes with
| the idea that LLMs can write useful code.
|
| I had a problem last week where I wanted to extract sheet
| names and selection ranges from the Numbers app for a few
| dozen spreadsheets. ChatGPT, came up with the idea of using
| Apple script and with a but of coaxing wrote a script to do
| it. I don't know ApplesScript and I really don't want to
| learn it. I want to solve my problem and its 10 lines of
| AppleScript did just that.
|
| We're nowhere near LLMs being capable of writing codebases,
| be we are here for LLMs being able to write valuable code
| because those concepts are orthogonal.
|
| 1. some, most
| gumballindie wrote:
| I am confused - the "code" you described is likely a google
| search away. Well I mean google has become useless but when
| it worked it was able to find such stuff in one search. So
| really all I am getting is that gpt is a better google.
| kelseyfrog wrote:
| I'm not quite understanding. It sounds like I was
| supposed to use google search before it stopped working?
|
| A great counterexample would be a google query which
| includes the answer in the results.
| umanwizard wrote:
| Are you using 3.5 or 4?
| badrabbit wrote:
| I feel like such a jerk for not wanting to use chatgpt for all
| that. It's not just mild paranoia about feeding it input I
| prefer be kept private but I just don't enjoy having someone
| else do half the thinking for me I guess.
|
| I mean, I don't like intellisense either (but simple
| autocomplete is fine). Perhaps it is because I only code to
| help with my job, I don't get paid to have a lot of good
| quality code output.
| sanderjd wrote:
| I think I would have felt this way when I was younger. But
| after writing code for over twenty years, I'm very happy to
| let computers do the boring half of the thinking, so that I
| can think about more interesting things.
|
| It is not intellectually stimulating for me to think about
| what the syntax for a dict comprehension is, or what exactly
| I'm supposed to do to map over the values of an array in
| javascript without screwing it up, or any of a million other
| kinds of minutia. Computers know the answers to these
| uninteresting questions.
| shanusmagnus wrote:
| That's what's been so striking for me -- the stuff that is
| fun and playful for me I get to do; and a bunch of stuff
| that I hated I can now offload, with the net result that I
| get to work at the level of abstraction that is most
| interesting and most human, vs acting like a human robot
| trying to unearth documentation, API examples, etc.
|
| There's no question about this being the right way to use
| it for me, but I wonder if this could introduce something
| bad for someone just starting out, who hadn't first got all
| the reps with the drudgery over decades? Still mulling on
| that.
| sanderjd wrote:
| Yeah, I've said a bunch that I'm worried about people
| starting out from scratch. So much of what I do after I
| get responses from LLMs is best described as "taste", but
| how would I have developed that taste without the years
| of slogging through?
|
| But I also think this is probably just a classic geezer's
| concern about kids being on my lawn, and it will probably
| work out just fine for these youths :)
| jprete wrote:
| Eh. I think the peak of computer ability was GenX. I'm
| not in that group but made up for it with sheer
| intensity. If you grow up on a phone you're not getting
| any of the mental modeling to get close to what the
| machine is doing and you're only going to be able to work
| with the limited tools of that level until you
| deliberately dive deeper.
| shanusmagnus wrote:
| I think both you and the GP are onto something important.
| I am one of the vaunted Gen-Xers (this is the first time
| someone has said anything nice about us, so thanks) and
| there is something to the idea that my understanding of
| systems goes down to assembly language (fully) and even
| CPU architecture (very sketchily) all the way up to,
| like, web frameworks. So for the stuff I'm usually doing,
| I understand several layers up and down, and that often
| seems valuable.
|
| This strikes me as the essence of expertise, the
| difference between talking to someone who's read a book
| or a review paper, vs someone who is a real expert at
| that thing. You can be quite competent and insightful
| from having done a modest amount of reading and thinking,
| but if you're seeing the Matrix, and know how all these
| forces are interacting with each other, that's just a
| whole other level. It makes an impression when you brush
| up against it.
|
| However: it always weighs on me how this is all a matter
| of framing. Like, I don't know the electronics. There's a
| level of metal that I don't get. Some of the really high-
| level stuff is now beyond me, too. I catch myself saying
| "I should really take x {weeks, months, years} and really
| grok that." And yet my actual experience suggests this is
| a mirage.
|
| More briefly: there are always more layers for a fuller
| understanding. It's hard to see how many of them are
| really useful. Maybe the kid who is 10x better than me at
| LLM collaboration will benefit more than from having a
| deeper stack. It's interesting to ponder how these
| different consequences will play out.
| sanderjd wrote:
| FWIW I'm a (geriatric) millennial, and we were totally
| taught all that same stuff. And yeah, it totally feels
| important to me to have this mental model up and down the
| layers. But I also do wonder whether we're just wrong
| about that, merely falling prey to nostalgia.
|
| My messy answer is that for many projects it's either
| neutral or an actual hindrance - I have to remind myself
| to pragmatically not care about stuff that won't matter
| for years at the project's expected growth rate - but for
| other projects it's very useful. I think the way to go is
| to seek out those kinds of projects, in order to avoid
| frustration all around.
| shanusmagnus wrote:
| Always important to be on guard for things amenable to
| self-congratulation. At least, I sure need to be on guard
| against it :)
| jprete wrote:
| I think a lot of the drudgery is lack of language
| quality. But this is still a better argument than I've
| seen before for using it.
| sanderjd wrote:
| I dunno, I've used all kinds of languages, from the ones
| people often consider lower quality to the ones people
| often consider higher quality, and they all have
| _something_ like this.
|
| And maybe there's some as yet unexplored design space out
| there for which this isn't true, but my prior is that
| we're actually just circling around some essential
| complexity at the core of the problem, which will never
| be eliminated.
| breckenedge wrote:
| It takes programming back to the pseudocode experience, but
| now the computer can fill in all the code bits really well
| about 75% of the time
| sanderjd wrote:
| Yeah, 75% seems a bit high, but it's a high enough
| percentage to be extremely useful to me.
| n4r9 wrote:
| Don't beat yourself up. As a mathematically-oriented software
| engineer I also have little to no interest in using LLMs to
| help with coding. It feels like the people that do are the
| builders, i.e. interested in quickly knocking up something
| that works most of the time. Which is great from a business
| perspective. I can't help but see my programming output as an
| artistic expression of my thought, and therefore find it
| difficult to give up the hands-on construction to others (be
| it LLMs or juniors).
| corethree wrote:
| Mathematically oriented software engineers have the most to
| benefit off of software assistance due to algebraic
| designs.
|
| As one myself LLMs don't feel like giving up control it
| feels like collaboration. You probably don't like
| collaboration.
| jprete wrote:
| Claiming that someone doesn't like collaboration because
| they don't want to use ChatGPT is a very unreasonable and
| biased take.
| bumbledraven wrote:
| Not especially more biased than GGP's claim that people
| who use LLMs as coding assistants are "builders, i.e.
| interested in quickly knocking up something that works
| most of the time".
| n4r9 wrote:
| Could you expand on the comment about "algebraic
| designs"?
|
| When I interact with an LLM it feels like I'm speaking to
| someone who lacks inherent conceptual understanding, but
| is doing their utmost best to bullshit me. This is
| problematic when it comes to algorithmic thinking.
|
| I sometimes need to solve problems that involve tweaking
| existing algorithms in somewhat novel ways. For example
| "k-medoid clustering but with various capacity
| constraints on clusters", or "contraction heirarchies but
| accounting for varying vehicle dimension restrictions".
|
| I love collaborating with smart colleagues to come up
| with ideas to solve these problems. Seeing chat-gpt fail
| to solve very simple traveling salesman type problems
| gives me little confidence that it can do novel
| conceptual tihnking.
|
| EDIT
|
| To test my own claims, I just tried asking Chat-GPT to
| make this modification to k-means clustering. It produced
| something that will give _a_ result but will likely not
| be very optimal. When prompted to refine the solution, it
| failed to understand the issue and instead proposed the
| exact same solution just with a bit more implementation
| detail.
|
| User
|
| Suggest a modification to the k-means algorithm where the
| number of elements assigned to each cluster is limited to
| a pre-defined maximum value.
|
| ChatGPT
|
| To modify the traditional k-means algorithm to limit the
| number of elements assigned to each cluster to a pre-
| defined maximum value, you can create a variation of
| k-means called "k-means with cluster size constraints."
| This modification ensures that no cluster exceeds the
| specified maximum size while still optimizing cluster
| centroids based on the sum of squared distances. Here's a
| high-level overview of the modified algorithm:
|
| 1 Initialize centroids: Start by randomly selecting K
| initial centroids, where K is the desired number of
| clusters.
|
| 2 Assign data points to clusters: Assign each data point
| to the nearest centroid based on Euclidean distance, just
| like in the traditional k-means algorithm.
|
| 3 Update centroids: Recalculate the centroids of each
| cluster by taking the mean of all the data points
| assigned to that cluster.
|
| 4 Check cluster sizes: After updating the centroids,
| check the size of each cluster. If any cluster exceeds
| the pre-defined maximum size, proceed to reassign some
| data points from that cluster to other clusters. Here's
| how you can do this: Identify the cluster(s) that exceed
| the maximum size. For each over-sized cluster: Sort the
| data points in that cluster by their distance to the
| cluster centroid in ascending order. Start reassigning
| the farthest data points to other clusters (the ones with
| the smallest distances) until the cluster size constraint
| is satisfied. Update the centroids of the affected
| clusters accordingly.
|
| 5 Repeat steps 2 and 3: Continue iterating between data
| point assignment and centroid updating until convergence,
| or until a predefined number of iterations have been
| reached.
|
| 6 Termination: The algorithm terminates when either the
| cluster assignments do not change significantly between
| iterations or after a fixed number of iterations.
|
| Here are a few things to consider when implementing this
| modification: You will need to
| experiment with the order in which you reassign data
| points from over-sized clusters to minimize the impact on
| the overall clustering quality. You should
| set an appropriate stopping criterion to prevent the
| algorithm from running indefinitely. Be
| prepared to handle situations where it is impossible to
| meet the cluster size constraint while maintaining good
| cluster quality. In such cases, you may need to relax the
| constraint or consider alternative clustering methods.
|
| This modified k-means algorithm with cluster size
| constraints allows you to control cluster sizes while
| still finding meaningful clusters in your data.
|
| User
|
| Your proposed solution has an issue that points might be
| reassigned even if there are clearly no other suitable
| clusters. Please tweak the solution to avoid this issue.
|
| ChatGPT
|
| To address the issue of potentially reassigning points
| even when there are no other suitable clusters, we can
| modify the approach by introducing a priority queue or
| heap data structure to efficiently manage the
| reassignment process. Here's an improved version of the
| k-means algorithm with cluster size constraints:
|
| 1 Initialize centroids: Start by randomly selecting K
| initial centroids, where K is the desired number of
| clusters.
|
| 2 Assign data points to clusters: Assign each data point
| to the nearest centroid based on Euclidean distance, just
| like in the traditional k-means algorithm.
|
| 3 Update centroids: Recalculate the centroids of each
| cluster by taking the mean of all the data points
| assigned to that cluster.
|
| 4 Check cluster sizes: After updating the centroids,
| check the size of each cluster. If any cluster exceeds
| the pre-defined maximum size, proceed to reassign data
| points from that cluster to other clusters. Here's how
| you can do this: Identify the cluster(s) that exceed the
| maximum size. For each over-sized cluster: Create a
| priority queue (or heap) to store the data points in the
| cluster, ordered by their distance to the cluster
| centroid in ascending order. Start reassigning the
| farthest data points to other clusters (the ones with the
| smallest distances) until the cluster size constraint is
| satisfied. Update the centroids of the affected clusters
| accordingly. Continue this process until either the
| cluster size constraint is met or there are no more
| suitable clusters to reassign points to.
|
| 5 Repeat steps 2 and 3: Continue iterating between data
| point assignment and centroid updating until convergence,
| or until a predefined number of iterations have been
| reached.
|
| 6 Termination: The algorithm terminates when either the
| cluster assignments do not change significantly between
| iterations or after a fixed number of iterations.
|
| This modified approach ensures that points are only
| reassigned to clusters that are suitable and have room to
| accommodate additional points while maintaining the
| overall quality of the clustering solution. The use of a
| priority queue helps prioritize the reassignment of
| points to clusters with the least impact on their
| quality.
|
| Additionally, you should set an appropriate stopping
| criterion to prevent the algorithm from running
| indefinitely, and you may need to handle situations where
| it is impossible to meet the cluster size constraint
| while maintaining good cluster quality by relaxing the
| constraint or considering alternative clustering methods.
| corethree wrote:
| How is what you're doing mathematical? I mean you can
| call CS "math", but then I don't know what you mean by
| more "mathematical." Traditional cs algos are not what I
| term as more mathy from my pov. Maybe you can call stats
| "mathy" but this is more applied math and not too
| different from what "builders" do.
|
| Also what you're doing here is asking chatGPT for the
| answer. chatGPT is more effective via collaboration.
| Meaning instead of shoving the entire problem down it's
| throat and asking it to solve it, you ask it for advice.
| Ask it for bits and pieces of things.
| bumbledraven wrote:
| An LLM is going to be most helpful for topics that came
| up a lot during training. What you're discussing doesn't
| sound like it falls into that category.
| sanderjd wrote:
| I think the division is along a different axis than this
| one (or probably it's along multiple axes).
|
| I've always been more of a fastidious crafter than a "just
| get it built" person, but I also struggle with a blank
| page. I thrive on editing more than writing. Since forever,
| I like to get out something that works or mostly works, and
| then start carving on it until I like it.
|
| LLMs have been helping me get some ink on the page, but
| very little of what they suggest ends up in the final
| product.
| jprete wrote:
| I've observed for a long time that there's a lot of value
| in making a seed, a starting point, for the thing a group
| needs to create. And that's exactly the reason - new text
| is harder than criticism of the old.
| sanderjd wrote:
| Yep! But some people do seem to thrive more with a blank
| page.
|
| Supposedly Tom Robbins writes books entirely by putting
| one word after another starting with the first one and
| finishing with the last one. I don't know if that's
| apocryphal, but I do think that's closer to the process
| for some people.
|
| But if I were a writer, I'd be squarely in the "get out a
| first draft, it will be like pulling teeth, but just get
| something down; then you can do the fun part of revising
| and polishing".
| deelly wrote:
| I know exactly why I don't want to use ChatGPT.
|
| I love to write code, I love to modify existing code too.
|
| I do not love to read and then fix code after someone all the
| time. With ChatGPT I have to read then understand then fix
| code after ChatGPT every time.
|
| Also, I do not love to fix code that often contains
| hallucination.
| bumbledraven wrote:
| First, are you sure using GPT-4?
|
| Second, have you tried pasting any syntax errors you get
| back into the chat window? Usually, GPT will try to fix
| them.
|
| Third, you can have GPT write a function for you and then
| write a different version of the function using a different
| algorithm along with a test (e.g. a fuzz test) to check
| whether two functions produce the same output given the
| same input. This makes it less likely that an error will
| slip through because both algorithms would have to be
| produce the same incorrect output for the same input.
| throjwbahrnd wrote:
| [flagged]
| reaperman wrote:
| A lot of this seems like a nerd's fantasy. I share these
| fantasies / desires, but I don't think its a sober, realistic
| take on what's most likely.
|
| > Even if an LLM could provide me with a recipe that perfectly
| suits what I'm looking for, I wouldn't want to give up the
| experience of using a recipe search engine and browsing through a
| large collection of recipes.
|
| Me too, but allrecipes.com has already switched from "search for
| what you want" to "we'll tell you what you want". This is a UX
| pattern that I hate but has proven a winner across many apps
| lately - e.g. TikTok. Streaming music still allows you to build
| playlists of specific songs, but auto-built radio stations are
| filled with a suspicious amount of whatever the major labels are
| pushing this quarter. Netflix/etc has shockingly fuzzy search
| which largely pushes whatever they want you to watch rather than
| what you're searching for. YouTube is mostly also push rather
| than pull today.
|
| I expect everything to continue moving that direction, against
| the wishes of the power users. The majority of users seem to go
| for the simpler UX, even if they sometimes complain about
| quality.
|
| > In an ideal world, I'd like to have the underlying model be a
| swappable implementation detail. Llama 2 and similar developments
| make me optimistic.
|
| This is a pipe dream. LLMs may be hot-swappable by developers but
| for 99% of apps + OSes this wont be a user-configurable thing.
| vishnumenon wrote:
| Author of the piece, and I... can't really argue with any of
| this, tbh. I'll admit both those parts you called out were
| probably heavily tinged by my own desires, and your more-sober
| predictions are a very reasonable counterargument for what will
| happen in the general case. I suppose, especially regarding
| swappable LLMs, I _do_ only expect it to be an option for devs
| or sophisticated users; I assume that most folks probably
| wouldn't care, I'm just hoping there's enough of us that do
| care that at least some options offer that swappable
| functionality. Fwiw, I also use Linux (Fedora) as my daily-
| driver, and I'd be more than content if the predictions from
| this post came true in a similar vein, e.g. as an OSS option
| (or family of OSS options) that some subset of users can opt to
| use.
| greenie_beans wrote:
| > Me too, but allrecipes.com has already switched from "search
| for what you want" to "we'll tell you what you want".
|
| has anybody ever heard of a cookbook? it's the perfect ux for
| this. especially if you have a lot of different ones. even
| better if you collection is mostly physical copies.
| reaperman wrote:
| Yes but Allrecipes.com didn't cost me hundreds of dollars to
| get 20-30 high quality cookbooks and had 10,000+ recipes.
| More importantly, I could trust that the highest-rated
| recipes, while not necessarily the "best", would be stupid-
| proof. The only way that recipes got universally high
| feedback from the average home cook on allrecipes.com is if
| you could accidentally double or halve any ingredient and it
| would still taste good. Cookbooks often contain recipes
| which, while better, are also more particular and require a
| higher skill floor.
|
| I could also quickly filter against recipes which contained
| ingredients I didn't like, or filter for recipes which used
| ingredients I already have on hand.
| vishnumenon wrote:
| OP here, as someone who does love cooking, I've gone down
| this route pretty heavily in the last few years - been
| growing my collection of physical cookbooks and definitely
| enjoy flipping through them in search of inspiration. So,
| yeah, very much endorse the cookbook UX!
| [deleted]
| AmericanOP wrote:
| I am actually surprised how little UI innovation has bubbled up.
| forward-slashed wrote:
| Same. If you want to talk about it dm me on X @eating_entropy.
| jarulraj wrote:
| Nice writeup! Here is another example of using LLMs is to
| augmenting existing software that we are exploring --
| specifically SQL database systems. We are using LLMs inside a SQL
| query to power a "soft join" between SQL tables for when a
| correspondence is only implied (e.g. different address formats,
| etc.). --- Create a reference table that maps
| neighborhoods to zipcodes using ChatGPT CREATE TABLE
| reference_table AS SELECT parkname, parktype,
| ChatGPT( "Return the San Francisco neighborhood
| name when provided with a zipcode. The possible
| neighborhoods are: {neighbourhoods_str}. The response should an
| item from the provided list. Do not add any more words.",
| zipcode) FROM postgres_db.recreational_park_dataset;
| --- Map Airbnb listings to park SELECT
| airbnb_listing.neighbourhood FROM
| postgres_db.airbnb_listing JOIN reference_table ON
| airbnb_listing.neighbourhood = reference_table.response;
|
| More details on LLM-powered joins and EvaDB:
| https://medium.com/evadb-blog/augmenting-postgresql-with-ai-...,
| https://github.com/georgia-tech-db/evadb
| J_Shelby_J wrote:
| The modern internet and modern app experience has become so
| shitty. For example opening up Robinhood, transferring money from
| a bank account, and buying a stock is hidden behind a multitude
| of product driven dark patterns that turns what should be a low
| cognitive load task into a high cognitive load task. This is true
| for everything now days.
|
| I predict llm based agents will be used as a 3rd party layer on
| top of the modern web to work in users favor against
| enshitification.
| mywittyname wrote:
| > I predict llm based agents will be used as a 3rd party layer
| on top of the modern web to work in users favor against
| enshitification.
|
| I'm predicting the opposite -- LLMs will be used to turn Dark
| Patterns into Vantablack Patterns.
| alexyz12 wrote:
| Wouldn't this avoid a lot of ad exposure that companies are
| currently enjoying? Why would they want to give that up by
| allowing you to use your llm instead?
| intotheabyss wrote:
| If we're talking about the future here, it makes much more
| sense that you'd be buying stocks directly using currency
| stored on your phones hardware wallet through a DEX like
| Uniswap. In fact, you might just tell your phone that you want
| to buy X amount of stock, and it would do it all for you
| onchain.
| politelemon wrote:
| Some nice ideas here. I think some of these could see
| realisation, depending very much on how accessible those LLMs
| become.
|
| At the moment I'm sure there are only a couple of user interfaces
| that people know and will resist l reuse. After all they'll want
| to take very little risk and use what they've seen works in other
| places. The full screen ChatGPT style page, or those annoying
| chatbot pop-ups that sit in the bottom right hand corner of sites
| I don't care about. Something to keep an eye on and see what
| emerges.
| j-a-a-p wrote:
| My prediction: knowledge will start to be reformatted into an LLM
| directly and knowledge providers will stop publishing it
| otherwise. Thus the chat interface will both improve and protect
| knowledge access once the traditional formats are not published
| anymore.
|
| This will come together with the downfall of search, a prime
| driver why so much knowledge was published on the web. Search
| will start to drown in an explosion of generated AI content, and
| the case to publish your knowledge for the sake of SEO marketing
| will diminish.
| throwuwu wrote:
| If you can sell your knowledge to an existing audience and then
| add a special category with a higher price for companies
| training LLMs why would you take the financial hit of selling
| to a single customer where they can now make demands of you as
| your only source of revenue?
| j-a-a-p wrote:
| I don't get your reasoning. First not all knowledge is the
| source of revenue. Many products and services are supported
| by know how to implement, use and maintain. This kind of
| knowledge can benefit from protection.
|
| And if selling knowledge is the main revenue, why would
| transferring it to an LLM mean losing the opportunity to sell
| it multiple times? Au contraire.
|
| For any category I assume the owner of the knowledge keeps in
| control and my case is that a LLM can be beneficial for them.
| christkv wrote:
| Back to human curated web directories we go.
| kordlessagain wrote:
| Models still need to search. Tuning and reference augmented
| generation go hand in hand.
| j-a-a-p wrote:
| Indeed, but search exist for humans. And if search becomes
| unusable because the web gets filled with AI noise, humans
| will stop using search.
|
| And also for models, to feed them with data generated by AI
| seems like an issue to me.
| Traubenfuchs wrote:
| I feel like us not being in that future right now means we won't
| get there so fast.
|
| What's missing to get all of this now? What recolutionary
| research, product development that hasn't happened yet will
| happen in the coming year?
|
| To me it looks like LLM tech is stagnating, after the hype peak
| we are close to the trough of disillusionment.
| frabcus wrote:
| Part of the problem is that GPT-4 inference is too expensive to
| roll out at scale with current GPU availability and cost, so
| even basic features aren't generally available (e.g. your word
| processor writing for you) or if they are the model used is
| cheaper and not as good.
|
| Partly it just takes time - it will overall take (I think,
| based on previous similar changes like the web) 20 years before
| the ideas from the current generation of LLMs are built out and
| integrated into products and made into new products and it is
| all done. People and organisations take time to change.
| amelius wrote:
| The problem with LLMs as I see it is that they make logic
| errors all the time, and somehow LLMs themselves are not smart
| enough to reason about their own reasoning.
| geuis wrote:
| Ok. I appreciate they didn't use Medium as a blog post. There's a
| lot of good engineering knowledge currently locked behind the
| Medium "sign in" interface. It's dumb and stupid.
|
| But just to voice an opinion, please kill the lengthy paragraph
| levels of fluff in blog posts. I don't want to say my opinion is
| influenced by shitty blog recipes and research papers, but it is.
| So stop it.
|
| Just say what you need to say in bullet points at the beginning
| and fill in the details further on.
| dleeftink wrote:
| While I agree some longform articles could use a bulleted
| summary, I think the act of blog-writing is as much an exercise
| of the writer coming to terms with the subject as us enjoying
| the piece. Abridging an idea comes easier after exploring its
| breadth and width, and I am supportive of anyone who tries it
| out in the open.
| CharlieDigital wrote:
| I agree with this and often even find myself leaving drafts
| around to read, re-read, and edit as I flesh out the ideas
| and thoughts in my own brain.
|
| Writing in long form is its own process of mental synthesis.
| jprete wrote:
| People who want AI to write for them don't understand this
| process.
| mediumsmart wrote:
| You nailed it. In 2027 the AI is going to write the fluff for
| the Author and then extract the bullet points for the reader -
| Everybody saves time, winwin.
|
| _and for some there will be a "please elaborate" command of
| course_
| dleeftink wrote:
| One man's fluff is another man's.. recommendation algorithm?
| liampulles wrote:
| My prediction is that LLMs are going to be used almost
| exclusively for views over commands. They are simply too
| unpredictable.
|
| I'm more optimistic than the author about how useful LLMs may be
| for chat based interfaces - I don't think it is appreciated in
| tech how many people are (still) computer illiterate in the
| world, and natural language can be a big improvement in usability
| for the kinds of usecases these users need.
| amelius wrote:
| Take over simple system administration tasks such as (of course
| giving it full shell access):
|
| - install this nVidia driver and make it work with pytorch
|
| - get this ethernet connection to $IP working
|
| - schedule a daily cron job to make an incremental backup of this
| harddrive, don't store duplicate files
| klibertp wrote:
| You've got nerves of steel. It can, and will, hallucinate sudo
| rm -fr / as a step necessary for configuration at some point
| (it's even easy to justify by, say, missing the mention of this
| having to be in a chroot or a container). Russian roulette with
| your data and setup on the line. Not sure I'm willing to try...
| amelius wrote:
| Step 1: use a filesystem that supports snapshots ;)
|
| Anyway, if LLMs can write computer programs (see Copilot),
| then surely they can do simple administrative tasks ...
| munificent wrote:
| _> Basically, the thinking goes, once we're able to express our
| desires to computers in natural language, and once natural-
| language agents can carry out actions on our behalf, we'd no
| longer need the myriad of individual task-specific applications
| that exist today. Personally, I neither believe in nor desire
| this outcome._
|
| Strong agree.
|
| I find it very telling that the kind of people who advocate for
| chat-like software are often managers and executives. Sure, if
| the kind of person you are is one that enjoys giving verbal
| orders to people, it makes perfect sense that that's the kind of
| job you'll seek, and the kind of software you'll want.
|
| But for the rest of us creative hands-on people who like to feel
| that we're making things through direct manipulation, talking to
| a computer is just about the least joyful activity I can imagine.
| christkv wrote:
| I want to talk to your supervisor. No problem I'll connect you.
| Hi I'm supervisor bot how can I help you?
| jaynetics wrote:
| > Even if an LLM could provide me with a recipe that perfectly
| suits what I'm looking for, I wouldn't want to give up the
| experience of using a recipe search engine and browsing through a
| large collection of recipes. Even if an LLM could provide me with
| restaurant recommendations based on my preferences, I'd still
| seek out a map-based UX for exploring the variety present in my
| vicinity. The desire to replace all UX with LLMs seems like a
| desire to replace all serendipity with efficiency, and I think
| (or hope) that such a transition is much more appealing in theory
| than it would be in practice.
|
| I guess the question is: how much of our web or software use is
| leisurely browsing (reading news or HN would be other likely
| candidates for this category) and how much is more task-like,
| e.g. send a message to some friends, add a note to a specific
| list, order some groceries?
|
| We might also want to consider how much of a role such private
| use of software plays in shaping UX trends. If business software
| (sheets, Photoshop, CAD etc.) can be sped up with chat input, it
| will be, and people will be expected to use the quickest UI.
|
| This is not to say that browsing will disappear, but I can
| totally see it being relegated to a second class UI in the long
| run, even in applications where it's currently the obvious
| choice, just because our default UX expectations will be
| different.
| layer8 wrote:
| > If business software (sheets, Photoshop, CAD etc.) can be
| sped up with chat input, it will be, and people will be
| expected to use the quickest UI.
|
| I have a hard time seeing chat input become the primary UI for
| that class of applications, unless you can delegate complete
| tasks to it. As an analogy, for driving a car, I can see voice
| commands replacing the steering wheel _if_ we reach full self-
| driving capabilities, but absent that, the steering wheel and
| gas /breaking pedals will remain the more efficient and
| practical UI (even ignoring safety concerns).
| xbmcuser wrote:
| I think the biggest change will be users will increase my
| parents don't know how to use Photoshop are not tech inclined
| they won't be touching up photos of their grand child. But
| give them an option of just asking the app to do something
| and they will as the learning curve goes down dramatically
| particlesy wrote:
| We wrote about Jane using Particlesy Retrieval-Augmented-
| Generation platform to create and share Recipe chatbots with
| her friends - https://www.particlesy.com/2023/07/25/rag-in-the-
| kitchen-jan...
| CharlieDigital wrote:
| > I guess the question is: how much of our web or software use
| is leisurely browsing
|
| I think the author's sentiment here is different. There's a
| personal subjectiveness when it comes to things like recipes.
| It could come down to the presentation (photos, narrative), an
| added ingredient in one that piques your interest and curiosity
| (a chili recipe with dark cocoa powder?!), or other subjective
| difference that is experienced differently by each of us.
|
| The other aspect is mental bookmarking or "what ifs". Maybe
| I'll try _this_ recipe _this_ time, but I might come across
| other recipes I want to try some other time or I 'll find an
| author that I really vibe with. That process of discovery is
| lost with LLMs today
| croo wrote:
| I'll tell you my vision which is kinda long term - like 20-30
| year from now on. I think the future is that everyone will have
| their own personalized AI assistant on their phone. Internet as
| it is will be mostly useless because only robots will be able to
| wade through the generated shit ocean and the next generation
| will see it as the current see the TV - unimportant old boring
| low-entropy data which is not entertaining anymore.
|
| There will be a paradigm shift where our-customers-are-ai apps
| appear and most stuff will need to have an API which makes AI
| able to connect and use those services effortlessly and without
| error because who don't want to tell his assistant to "send 5$ to
| Jill for the pizza"? There will be money in base AI models you
| can choose(subscribe to) and what it can and cannot do for you.
| It will still be riddled with ads and now it's your personal
| assistant who can push any agenda to you.
|
| Operation systems will become a layer under the assistant ai.
|
| You will still talk on/to your phone.
|
| I guess free software will be more important than ever.
|
| Free ai assistants will be available and computing power will be
| there to run it on your phone but all the shit we've seen with
| open Vs closed source, Linux Vs Windows, walled gardens whatnot
| will go another round this time with free open public training
| data assistants Vs closed-but-oh-so-less-clumsy ones.
|
| Security problem will be plenty like how to hide your AI
| assistant custom fingerprint? Authentication and authorization
| system for AI? How much someone else personal assistant worth?
| How to steal or defend it?
| tines wrote:
| Do you think that this will all function as one giant
| homogenizing force at the societal level? The AIs will all be
| trained on the same data, and so will have the same opinions,
| beliefs, persuasions, etc. It seems like everyone having AIs
| which are mostly the same will maximize exploitation, and
| minimize exploration, of ideas.
| _Algernon_ wrote:
| Is that any different than media before the internet consumed
| it all? Media consisted of a couple of news stations, a
| couple of TV stations and that was mostly it.
|
| I'm also not sure that the recent broadening of media has
| been a net benefit to society. Look at the degree of
| polarization in recent years. At a certain point
| heterogeneity is no longer a societal good.
| og_kalu wrote:
| There are a million different beliefs, opinions etc in the
| corpus LLMs get trained on and they can predict all of it. It
| doesn't have to have the same opinions.
| tines wrote:
| Sure, but the probabilities of those beliefs won't be the
| same as each other, and they will be the same between all
| users, so that doesn't address my point.
| og_kalu wrote:
| again that's up to who's training the models and/or the
| user. Bing is GPT-4, same exact pre-training but it
| sounds nothing like chatGPT-4.
|
| LLM probabilities are dynamic. They change based on
| context. If you want it to behave in a certain way then
| you provide the context to engineer that.
|
| a particular belief system being most present in training
| doesn't mean an LLM will always shift probabilities to
| that system. Such prediction strategies would be awful to
| fulfil its training objective. Getting it to shift to
| even the most niche belief is as simple as providing the
| context to do so.
| tines wrote:
| > again that's up to who's training the models and/or the
| user.
|
| True, but training is expensive, I imagine that only a
| few actors will train the popular LLMs, exactly as we are
| seeing today.
|
| > LLM probabilities are dynamic. They change based on
| context. If you want it to behave in a certain way then
| you provide the context to engineer that. ... Getting it
| to shift to even the most niche belief is as simple as
| providing the context to do so.
|
| I thought so too, until I tried to get it to agree that 1
| + 1 = 3. It would not do that, no matter how much context
| I provided, likely because the probabilities in the
| underlying data were so skewed.
| smokel wrote:
| In 20-30 years I most certainly do not want to use a phone
| anymore.
|
| I grew up without the things, and boy was that fun.
| xmprt wrote:
| Do you ever wonder if that's because of the growing up part
| and not the phone part? Growing up for most people tends to
| be pretty fun and exciting compared to adult life. And with
| or without phones, the 80s and 90s were a very different time
| when it came to kids being able to go out and play outside on
| their own. Move to a country where it's common for kids to
| play outside and you'll see that times aren't much different
| even though kids all have phones. In a way, it's easier
| because now you're just one text and location share away from
| meeting up with them.
| redwall_hp wrote:
| Growing up in the time where Palm and Windows CE were a
| thing, I knew having a capable pocket sized computer was an
| inevitability, and couldn't wait for it. And it's great: I
| would fucking hate not having modern mobile banking,
| communications tools, maps, calendars and the ability to
| look anything up immediately.
|
| The internet was more fun pre-smartphone, but that's
| because of the demographic change brought on by a new
| Eternal September, not the existence of mobile computers.
| We went from the internet being the domain of interesting,
| creative people who made things for fun to "basically
| everybody."
| Workaccount2 wrote:
| Anything long term is meaningless to think about, besides just
| the fun.
|
| AI on it's current track is going to so radically reshape
| society that it will be totally unrecognizable to people today.
| Society in it's current form makes no sense when there are
| smarter and cheaper non-human workers available.
| semi-extrinsic wrote:
| There is a huge number of people - hundreds of millions -
| employed today that could quite literally be replaced with
| small shell scripts. Yet they are not being replaced. There
| is no reason why AI will not similarly fail to bring forth
| the revolution.
| thfuran wrote:
| Which people exactly?
| wbm1 wrote:
| An LLM/AI companion based on your ledger, that grows and
| evolves with you, acting as a sort of Socratic daimon, a
| psychologic twin, assistant, advisor, and sparring partner.
| Like a journal that talks back and thinks with you. It'd need
| to be only personally accessible and safe/private. Biometric
| access and local running could solve this.
| croo wrote:
| Exactly! Most will have a name given by its owner, a pet of
| sort but much more in function. You will need to reach a
| certain age to get it, the beginning of adulthood.
|
| People will mourn them and there will be real world AI
| cementeries.
|
| Diffie Whitfield envisioned an internet highway where every
| computer is connected to every other in 1974 and then went on
| to find out how to do that communication in secure
| channels.[1]
|
| I think my vision is quite tame and deductible from the
| current situation compared to his.
|
| [1] according to Singh Simon: The Code Book
| InitialLastName wrote:
| > You will need to reach a certain age to get it, the
| beginning of adulthood.
|
| Not a chance will whatever capitalist figures out how to do
| this allow a measly cultural restriction keep them from
| pushing that age deep into childhood.
| wbm1 wrote:
| The more personal value it holds, the more risk it has.
| Imagine gaining access to this digital daimon of someone,
| it'll be like accessing their most inner thoughts. The
| upside however could be exponential personal growth. I've
| seen many examples of real life twins that basically live
| as a superhuman individual. E.g. the Liberman twins. This
| tech could be a digital equivalent of that.
| pixl97 wrote:
| In outright totalitarian countries government access to
| your agent will be mandated.
|
| In more democratic countries we'll see lots of suits and
| court cases over getting access to these agents and
| assigning intent to your IRL actions based on your
| 'thoughts' with the AI.
| brandall10 wrote:
| Small correction - Daniil and David Liberman are just
| brothers, not twins.
| intended wrote:
| This is the dream. That said - Gen AI on its own wont get us
| to helpers/Daemons.
|
| Right now, if you want to build something like a daemon you
| will need multiple agents. When a task needs to be delegated,
| the central control system needs to be able to spin up a few
| processes and get them going.
|
| You can do this right now. You can create an ensemble of
| personalities/roles (jr dev, sr dev, project manager) and
| have them plan.
|
| They do a good job, if you are monitoring it. You can break
| up the plan into chunks, spin up more instances, distribute
| chunks and have those instances work on it.
|
| Sadly this cant happen, and I think these are fundamental
| limits to Generative AI. Right now personas just go ahead and
| "pretend work" - they say we "I am now going to go and come
| up with a project plan".
|
| You have a dependency where output from all prompts must be
| actionable, or verifiable. If output is off, then it
| snowballs.
|
| This is not a tooling, or context window issue. This is a
| hard limit to what Generation can achieve. Its impressive
| that we got this level of emergence, but when you look at
| output in detail, its flawed.
|
| This is the verification issue, and verification (or
| disproving something) is the essence of science.
|
| Maybe something can be added to it, or entirely new
| structures can be built - but generation on its own will not
| take us over this threshold.
|
| Right now, LLMs are more like actors. They are very good
| actors, but you dont get your prescriptions from actors.
| hirundo wrote:
| > the next generation will see it as the current see the TV -
| unimportant old boring low-entropy data which is not
| entertaining anymore.
|
| Don't you mean high-entropy data? High entropy data would be
| less orderly, more compressible, and have a lower signal to
| noise ratio ... like TV shows compared to a textbook.
| inimino wrote:
| Low entropy data is what's more compressible. High entropy
| means unpredictable, which could mean high noise (like TV
| static which is incompressible) or high signal as GP
| intended.
| [deleted]
| hirundo wrote:
| Thank you. I just learned about Shannon Entropy and that it
| grows with information content. The negative sign in the
| formula is due to the negative log of the normalized
| population probability.
|
| https://math.stackexchange.com/questions/395121/how-
| entropy-...
| inimino wrote:
| Yes. You can also take the log of the reciprocal
| probability (or "luck") and then you don't need the
| negative sign. This value is the expected number of
| trials you would need for the outcome to occur once. I
| find this presentation a bit more intuitive. See also
| Boltzmann entropy S = k log W which takes this form.
| mywittyname wrote:
| Entropy is the "signal" within the noise.
| tines wrote:
| Not necessarily. Pure noise has high entropy.
| jprete wrote:
| For a bit there it didn't sound too bad!
| realce wrote:
| You'll be a God, but a God who has to look at ads all the
| time, and your angels will... also be ads.
| bostonsre wrote:
| If your interface to the internet is a locally running open
| source ai assistant, couldn't you just tell it to strip out
| ads from the information it returns? It could change the
| internet economy some.
| pixl97 wrote:
| Eh, if OpenAI gets their way, your local AI will be
| banned as being too dangerous.
| Tagbert wrote:
| If you have the right subscription level for your daemon.
| tarasglek wrote:
| @vishnumenon, thanks for writing this up. I might do a followup
| blog on this, for now here is a comment :)
|
| This article is close to my heart as I've been working on
| craftcraft.org with similar perspective.
|
| 1. Chat UX Consolidation: I agree that having crappy chat UIs
| everywhere is very suboptimal. Perhaps having a complete UX as a
| component is another solution here. We took many months to get
| http://chatcraft.org from prototype to an ergonomic productivity
| tool. Highly unlikely such attention will be paid to every chat
| UI integration.
|
| 2. Persistence Across Uses. This one is tricky. We keep all of
| our history client-side...but after using it this way, having a
| shared history server-side and having it pulled in as relevant
| context would be a nice improvement.
|
| 3. Universal Access: It's super weird to have LLMs restricted to
| providing output that you cut/paste. We have integrated pretty
| slick openai function interface to allow calling out to custom
| modules. So far we integrated: pdf conversion/ingestion,
| clickhouse analytics and system administration using a
| webrtc<->shell connector. Demo here:
| https://www.youtube.com/watch?v=UNsxDMMbm64
|
| I've also investigated teaching LLMs consume UIs via
| accessibility UIs. I think this is underexplored. Blog post on
| that here: https://taras.glek.net/post/gpt-aria-experiment/
|
| 3b. LocalLLMs. These have been underwhelming so far vs openai
| ones(except maybe WizardCoder). Industry seems to be
| standardizing around openai-compatible REST interface(ala S3
| clones). We have some support for this in a wip pull req, but not
| much reason to do that yet as the local models are relatively
| weak for interactive use.
|
| 4. Dynamically Generated UI & Higher Level Prompting: I do a lot
| of exploration by asking http://chatcraft.org to generate some
| code and run it to validate some idea. Friend of mine built basic
| UX for recruiting pipelines, where one can ingest resume pdfs
| into chatcraft and via custom system prompt have chatcraft become
| a supervised recruiting automation. We also do a lot generation
| of mermaid architecture diagrams when communicating about code. I
| think there a lot of room for UX exploration here.
|
| Now a few categories that weren't covered:
|
| 1. Multi-modal interaction: It's so nice to be able to have chat
| with the assistant and then switch to voice while driving or to
| input some foreign language. I think extending UX from chat to
| voice and even video-based gestures will make for an even cooler
| AI assistant experience.
|
| 2. Non-linearity in conversations: Bots are not human, so it
| makes sense to undo steps in conversation, fork them, re-run them
| with different input params and different model params. Most of
| my conversations in chatcraft are me trying to beat llm into
| submission. Example: tuning chan-of-density prompt
| https://www.youtube.com/watch?v=6Vj0zwP3uBs&feature=youtu.be
|
| Overall, really appreciate your blog post. Interesting to see how
| our intuition overlaps.
| amelius wrote:
| Your back button does not work!
| forward-slashed wrote:
| Really good stuff, but some minor things: your url doesn't
| work; went to your twitter profile, and it seems you meant
| https://chatcraft.org? Also, you are un-dm-able on twitter. (I
| am @eating_entropy if you want to talk more)
| tarasglek wrote:
| that's the right link :)
|
| would be great to chat on discord
| https://discord.gg/JsVe9ZuZCn
|
| (updated discord link)
| jarulraj wrote:
| The discord link seems to be not working. Just a heads up.
|
| The YOLO example on your Github page is super interesting.
| We are finding it easier to get LLMs to write functions
| with a more constrained function interface in EvaDB. Here
| is an example of an YOLO function in EvaDB:
| https://github.com/georgia-tech-
| db/evadb/blob/staging/evadb/....
|
| Once the function is loaded, it can be used in queries in
| this way: SELECT id, Yolo(data)
| FROM ObjectDetectionVideos WHERE id < 20
| LIMIT 5; SELECT id FROM
| ObjectDetectionVideos WHERE ['pedestrian', 'car']
| <@ Yolo(data).label;
|
| Would love to hear your thoughts on ChatCraft and a more
| constrained function interface.
| tarasglek wrote:
| I'm actually doing a lot of work with databases and LLMs.
|
| I enjoyed postgresml and evadb has been on my radar to
| try next. Would love to connect.
|
| (updated discord link)
| alluro2 wrote:
| I was hoping for some clever ideas about direction of software /
| UIs, and new use-cases for LLMs / AI, since for now I'm still
| struggling and have a lack of vision, it seems.
|
| For example, I work on developing a logistics management and
| route optimization platform. If I try to envision new features
| that could be unlocked through AI or just LLMs, I basically get
| nothing back from my feeble brain, that I would fit into this
| category. E.g. - automate incident handling (e.g. driver broke
| down, handle redirection of other driver, handover of goods,
| reoptimize routes) - but the implementation would be just a
| decision tree based on a couple of toggles and parameters - no AI
| there? Other things that come to mind - we already use ML for
| prediction of travel times and service durations - it's a known
| space, that I refuse to call AI.
|
| Apart from serving as an alternative and sometimes more efficient
| interface for data queries through NLP (e.g. "tell me which
| customers I had margin lower than 20% on, due to long loading
| times and mispackaged goods" - even then, all the data already
| needs to be there in appropriate shape, and it's just replacing a
| couple of clicks), I really fail to see new use-cases / features
| that the current state / hype for AI / LLMs unlocks.
|
| Am I just lacking vision? Are there opportunities I'm grossly
| overlooking?
| 6510 wrote:
| Turn the company jingle into a heavily distorted guitar track,
| make a database with 3d models of drivers, locations and drone
| footage, from departure to delivery including the people
| driving desks, then have the llm generate a movie with
| narration in a dark voice. Dealing with broken down vehicles is
| an opportunity to brag and show off.
| jarulraj wrote:
| Can LLMs help in cleaning up the logistics database -- like
| handling different variants of an address? Here is an example:
| https://medium.com/evadb-blog/augmenting-postgresql-with-
| ai-....
| vorpalhex wrote:
| Problem identification.
|
| Given all the log data for the last N packages, analyze for
| anomalies and hypothesis as to their cause. Eg is there a
| specific shipper, warehouse or driver causing problems?
|
| ML does well when you have too much data for a human to wrangle
| and the search target is well described.
| CaptRon wrote:
| Try asking chatgpt for some ideas.
| sanderjd wrote:
| Unironically, I've done this sort of thing.
|
| Not too impressed with the results though.
| suoduandao3 wrote:
| Ideas are probably the last thing humans will delegate to
| AI. We have needs and wants that Ideas help us meet, AI
| only sets priorities in a reactive way.
| sanderjd wrote:
| Yeah it's a pretty interesting experience actually,
| trying to use it for idea generation.
|
| It's like talking to a very well informed and generally
| competent person ... who has no spark of creativity or
| insight whatsoever.
|
| This does vary product to product - some are
| excruciatingly boring _by design_ - but I think they 're
| universally uninteresting just to different degrees.
| totallywrong wrote:
| My guess is that LLMs will become an absolutely incredible tool,
| to the point of being indispensable, _for software developers_.
| This demographic is highly biased and often magnify their
| usefulness based on that. For everyone else, they will continue
| to be an advanced search engine / copywriting assistant.
| davemateer wrote:
| https://chat.openai.com (GPT-3.5) to summerise this article:
|
| - summerise (then paste in the text)
|
| - explain like I'm 10
|
| Gave (the highlights)
|
| -- ai here
|
| 1. Chat consolidation
|
| 2. Remembering stuff
|
| 3. Access to Everything
|
| 4. Making things easier
|
| 5. Being helpful
|
| -- human here below
|
| I'd love for the author to be right in his predictions. Arguably
| current AI has made understanding this article '4. easier' for me
| to understand already.
| IanCal wrote:
| > I don't believe that natural language is an adequate medium for
| conveying instructions with the precision required for many
| applications. Moreover, the "inefficiency" involved in carrying
| out many digital tasks "manually" is a core driver of the joy
| that comes with using computers (for me and, I assume, for at
| least some subset of others). Even if an LLM could provide me
| with a recipe that perfectly suits what I'm looking for, I
| wouldn't want to give up the experience of using a recipe search
| engine and browsing through a large collection of recipes.
|
| But searching for places to eat and recipes to make is very much
| _not_ a precise search.
|
| IMO the reason _chat_ and not _input text and get an answer_ is
| so powerful is that it allows messy search with iterative
| refinement - just like talking to an expert. Just "chat input,
| result given" doesn't have that.
|
| I want to tell a recipe search I'm after a healthy light thing as
| it's hot. I want to get back options and then say "I don't really
| like cucumber though" and have it get rid of cucumber heavy
| recipes but leave in some salads and say "look this recipe has
| cucumber in but it'll be fine without it". Or "you asked for a
| chicken recipe but here's one with pork that should sub in just
| fine".
|
| For restaurants I want to get back some options and tell it
| "that's too expensive, this is a quick thing" and get back more
| hole-in-the-wall things. Tell it "Hmm, something spicy sounds
| good but I've been to those Indian restaurants before, I'm after
| something new" and get a recommendation for the Ethiopian place
| in town.
|
| > The current state of having a chat-ish UX that's specific to
| each tool or website (e.g. a Documentation Chat on a library
| documentation page, a VSCode extension, a Google Bard
| integration, a really-badly-implemented chatbot in my banking
| app, etc.) doesn't make any single one of those experiences more
| enjoyable, effective, or entertaining;
|
| Coding chat in my editor absolutely makes coding more effective.
| I want heavy integration around how it edits text, not a general
| chat widget.
|
| > The idealized role of persistence in LLM UX is also fairly
| obvious: it's easy to imagine an LLM-powered experience that
| remembers and "understands" all my previous interactions with it,
| and uses that information to better help me with whatever my
| current task is
|
| I sort of agree, but I absolutely detest hidden state about me. I
| _should not_ alter my behaviour just because I 'm worried about
| how that'll impact things. You see this regularly, I may avoid
| some weird youtube video (e.g. to see a weird flat earth take)
| because I don't really want the hassle of having loads of weird
| conspiracy stuff promoted or having to manually remove it from
| some list.
|
| Having said that, recipe search that remembers I hate cucumbers
| is great.
|
| I wonder if manually curated context will in general be better?
| Or maybe just for me.
|
| > I'm interacting with UXes that can remember and utilize my
| previously expressed preferences, desires, goals, and
| information, using that underlying memory across different use
| cases seems like low-hanging fruit for drastically reducing
| friction.
|
| The tricky part here is I switch contexts and don't want them
| bleeding into each other. My preferences for interaction around
| my kids and while at work are very different.
|
| > A small-scale and developer-centric example: I use GitHub
| Copilot in VSCode, and I was recently implementing a library with
| documentation that featured LLM-powered Q&A, and it felt bizarre
| to have two LLM-mediated experiences open that each had exactly
| half the info needed to solve my problem.
|
| I think here a split between _data sources_ and _frontends_ is
| key. This interaction is awkward, and should be combined (copilot
| should be able to reach out to that documentation).
|
| > locally runnable and open models are no match for GPT-4 (etc.),
|
| It's going to be more efficient to move compute to central
| places, the less they're used per person the more efficient it
| will be to have one central location process everyones things. A
| short taxi ride per week is cheaper than owning a car. However as
| uses grow (e.g. proactive llms), will this shift the equation
| towards locally runnable ones? A few queries a day and you're
| obviously better off not buying a h100. Constantly running things
| all day and if prices fall maybe that'll change.
| ilaksh wrote:
| All of this makes sense.
|
| I would like to add my own prediction for 2027. I believe in the
| next 4 years, much more comfortable and capable mixed reality
| glasses and goggles may be somewhat common. Also AI generation
| and streaming of realistic avatars will have advanced. Quite
| possibly this will use low-latency Wifi to stream from a PC.
|
| So if you want, you will be able to have a fairly realistic
| representation of the AI as a synthetic person in the room with
| you when you put the MR device on. It will have eye contact and
| seem quite similar to a real person (if you want). You will be
| able to just talk to it.
|
| Another thing that might become popular could be larger 3d
| monitors. The type that have some stereoscopic effect tuned to
| your exact position. So your AI helper might just live in a
| virtual window or doorway or something like that.
|
| You can actually already build something a bit like this, at
| least in 2d, without really inventing anything complex. You would
| use things like a HeyGen or D-ID API and maybe Eleven Labs or
| something. You won't get eye contact or a realistic 3d avatar
| that seems to be sitting on your couch, and there will be pauses
| waiting for it to respond. But theoretically, fast-forwarding
| several years, those things are not at all insurmountable.
| qwertox wrote:
| I really doubt it. Modified glasses are too much of a change,
| compared to earbuds which can be the bridge to the phone in
| order to provide a conversational assistant. For normal use
| there is almost no benefit of having something visual available
| without the need for manual interaction, which is the benefit
| of glasses compared to the smartphone screen.
|
| But being able to have a verbal communication with a chatbot is
| of immense help. It can be used while driving, while cleaning
| or doing anything else which requires the use of your hands or
| while they are dirty or covered with gloves.
|
| These glasses will be expensive for at least 4 more years and
| most of us just won't feel the need to invest in it.
| badcppdev wrote:
| When we can interact by talking to a 2D cartoon in a Zoom call
| then I guess we'll be X% towards your 2027 vision.
| BoxOfRain wrote:
| I'm not overly familiar with it but isn't this already a
| genre of gaming YouTuber?
| pomtato wrote:
| You can already do that with praktika.ai , they're in ed-tech
| and got ai avatars of sorts that you can "video-call" to :D
| sensanaty wrote:
| I'd rather chew gravel every day for the rest of my life than
| be forced into the hell of wearing a headset so that I can have
| my useless morning standups in a virtual room rather than on a
| 2D screen.
| thfuran wrote:
| 2037 maybe, but four years isn't very long.
| moffkalast wrote:
| Four years is an eternity in software, especially now that we
| can have LLMs write the first draft.
|
| Transformers were only invented six years ago after all. Some
| people are even very optimistically projecting that we'll
| reach the singularity in the next three.
| ffgjgf1 wrote:
| Feels a bit like dot.com
| thfuran wrote:
| Making comfortable and capable mixed reality glasses common
| is not primarily a software problem. In fact, I'd say the
| challenges are almost entirely unrelated to software,
| though there probably would be a need for a richer software
| ecosystem designed for mixed reality for them to really
| take off.
| theknocker wrote:
| [dead]
| prakhar897 wrote:
| I also wrote an article a while ago in the same vein.
| https://prakgupta.com/blog/envisioning_a_future_with_gpt
|
| The largest problem with a gpt future imo would be bot networks
| creating manufactured outrage. these will shift the decisions of
| policymakers towards those who controls these networks ie big
| corp.
| chx wrote:
| Nowhere near that, the largest problem will be when the
| misinformation will be manufactured on an unprecedented scale
| by these LLM. In the US alone some 300 000 people died from
| homemade artisan anti vaxx propaganda, it's very scary to think
| what will happen when GPT switches that to industrial scale.
| Doctorow called them "plausible sentence generators" and that's
| indeed what they are and it being plausible will make it
| deadly.
|
| https://www.npr.org/2022/05/16/1099290062/how-many-of-americ...
|
| > As the U.S. marks one million people dead from COVID-19,
| scientists suggest that nearly one third of those deaths could
| have been prevented if more people had chosen to be vaccinated.
| andsoitis wrote:
| > In the US alone some 300 000 people died from homemade
| artisan anti vaxx propaganda, it's very scary to think what
| will happen when GPT switches that to industrial scale.
|
| From a human moral viewpoint this is indeed despicable and
| worth considering mitigation.
|
| I am optimistic though that in the grand unfolding that
| natural selection brings, it will pressure an elevation of
| rationality, but with the cost of some human suffering.
| chx wrote:
| Natural selection is not fast enough. It operates over many
| generations but we know climate change is driving the
| expansion of zoonotic diseases. Consider within the last
| generation -- generally understood to be 25 years -- we had
| a SARS outbreak, swine flu, SARS-CoV-2, mpox outbreak just
| to name the big ones. It is extremely likely we will have
| more within the next 25.
| keskival wrote:
| The predictions the article makes are a bit unimaginative and
| shallow. The timeline is also somewhat extremely long. It's more
| like late 2023 than 2027.
|
| So, Language Model UX in 2024 according to me:
|
| - Pervasive: Virtual assistants are omnipresent, and integrate
| everything together. Like Alexa that is actually intelligent and
| can for example make you a custom app for interfacing with your
| banking following your preferences on-the-fly for you only. Web
| apps become meaningless as you are getting the UI you need
| customized, tailor-made, live when you need it. Agents go with
| you in smartphones or project to any device nearby. No need for
| authentication, bots know you.
|
| - Agentic: They will negotiate with each others all the time and
| present a unified interface to you no matter which system you are
| interacting with. The air is full of silent chatter. Things move
| when you aren't watching. Progress is decoupled from human input,
| attention and care.
|
| - Web searches and such are for bots. Answering phones is for
| bots. Making calls is for bots. Any person still grasping at
| these kinds of interfaces will notice all emails they get are
| from bots, and all emails they send are instantly answered by
| bots. Just let go, let the machines handle that, which brings me
| to:
|
| - Intermediation: No matter what you do, a bot will help you with
| it. Swiping Tinder? Don't bother, a bot does it better for you.
| Just lay back and relax. Ads become targeted to bots and
| truthful, because the bots won't forgive misrepresentation, ever.
| lewhoo wrote:
| I hope all the bold and rapid changes predicted here won't become
| reality so fast. I think the societal changes needed to somehow
| still function as a civilization will be too much for vast masses
| of people to handle resulting in some drastic decisions. I'm
| pretty pessimistic about this and can't shake it off, call it
| Yudkowsky syndrome.
| suoduandao3 wrote:
| One thing I hope we'll see is that the people with the big LLM
| servers try to be platforms as opposed to one-stop shops [1].
| With AI getting better and better at executing, I think best case
| we'll see an era where good novel ideas are the currency of the
| realm[2]. That would be great - coming up with novel ideas and
| thinking deeply about what we should be pursuing is about the
| best alignment with human nature I can imagine. But it can only
| happen if access to the LLMs themselves is cheap and hacker-
| friendly.
|
| [1] there's good arguments to evolve a business model in that
| direction, e.g. Apple beating blackberry not through superior
| hardware but a superior app store.
|
| [2] I'd be remiss not to plug my own recent oevre here,
| https://eucyclos.wixsite.com/eucyclos/contact-8-1 inspired by the
| difficulty of conveying positive emotions over screens. Advice
| from people who have built this kind of thing successfully is of
| course welcome.
| sgt101 wrote:
| 9/10 requests for a simple sql query get a working query.
|
| This isn't enough to enable a useful interface.
|
| It takes a lot of scaffolding to get an llm powered interface to
| actually work.
| jarulraj wrote:
| You might be interested in another way to use LLMs inside a SQL
| query. For example, LLMs can be used to power a "soft join"
| between SQL tables for when a correspondence is only implied
| (e.g. different address formats, etc.).
|
| More details here: https://medium.com/evadb-blog/augmenting-
| postgresql-with-ai-...
| liampulles wrote:
| I'm actively trying to scaffold an LLM for business usecases
| and my experience totally echoes this. I can tweak the prompt
| for a very representative set of training data, and then it
| vomits at a seemingly normal new case.
| arthurcolle wrote:
| have you tried to train a model based on your expectation
| context data and the outputs you want?
| cheevly wrote:
| like Cheevly: https://www.youtube.com/watch?v=lNCVO87cbHQ
| avindroth wrote:
| This space is surprisingly under-explored. Any idea in this space
| is basically new.
| [deleted]
| euroderf wrote:
| Perhaps I'm out to lunch here, but...
|
| No mention of the role of software requirements ? Has prompt
| engineering somehow replaced them ?
| j-a-a-p wrote:
| Title is misleading. More like what is under the hood in the near
| future, a technical perspective. I thought to find some
| inspiration on what kind of software we can expect.
|
| Nevertheless a nice and agreeable read.
___________________________________________________________________
(page generated 2023-09-20 23:02 UTC)