[HN Gopher] Malleable software in the age of LLMs (2023)
       ___________________________________________________________________
        
       Malleable software in the age of LLMs (2023)
        
       Author : tosh
       Score  : 74 points
       Date   : 2024-05-18 09:12 UTC (13 hours ago)
        
 (HTM) web link (www.geoffreylitt.com)
 (TXT) w3m dump (www.geoffreylitt.com)
        
       | eschneider wrote:
       | I'll worry about this when users can reliably write useful
       | specification documents. Garbage In, Garbage Out and all that.
        
         | thejohnconway wrote:
         | If the thing you want it to do isn't too unusual, LLMs can
         | guide you into doing something vaguely sensible.
         | 
         | This is the one area of AI I'm actually pretty positive about.
         | Computing largely passed people by, and computers have not
         | lived up to their potential. I could see this approach making
         | computers more useful for a large number of people.
         | 
         | Especially semi-technical people who's specialty isn't
         | programming.
        
           | v3ss0n wrote:
           | > Especially semi-technical people who's specialty isn't
           | programming.
           | 
           | That would be worse kind . Imaging fixing bug of those people
           | with LLM Hallucinated code that runs but having wrong logic
           | all over the place.
           | 
           | I reduced use of LLM for coding these days. I only ask it to
           | generate templates or write some repetitive codes and
           | sampledata.
        
             | waldrews wrote:
             | Cool how we're far enough into the adoption cycle that 'I
             | reduced use of LLM' is a mainstream thing to hear among
             | sophisticated techies.
        
               | mattgreenrocks wrote:
               | Some of us haven't even incorporated LLMs into our
               | development workflows yet. :)
        
           | yosefk wrote:
           | I do not envy a non-programmer stuck with buggy code
           | generated by an LLM.
        
         | Glench wrote:
         | I don't know if the intention of the article was to stoke worry
         | but actually embrace as opportunity! Users being able to make
         | their own software for their own needs is a worthy and
         | beautiful goal. It's like if people could only eat what was at
         | restaurants and not cook for themselves.
         | 
         | And of course with iteration and feedback loops people can
         | definitely learn how to specify what they want in a fairly
         | precise way.
        
           | worldsayshi wrote:
           | However, the easier programming gets the less people who
           | doesn't know it need to do it because it's more likely
           | somebody has already solved their problem.
        
       | Mathnerd314 wrote:
       | > Turning a natural language specification into web scraping code
       | is exactly the kind of code synthesis that current LLMs can
       | already achieve.
       | 
       | I wish, I have tried. LLM's don't understand the DOM. Unless it
       | is as simple as the address being in element id=address, an LLM
       | is useless for generating scraping code. You are better off with
       | an element picker and some heuristics to generate a selector /
       | xpath query. Now there are some specialized models, I found a
       | paper that takes the DOM tree and fits a vector to each node, but
       | I think they are too much effort for little gain, unless someone
       | integrates them into an open source scraping library so they are
       | easy to use.
        
         | worldsayshi wrote:
         | >You are better off with an element picker and some heuristics
         | to generate a selector / xpath query.
         | 
         | Bummer. I wanted to try my hand at this. There has to be some
         | trick where you can combine LLM and some element picker to get
         | a really robust solution right?
        
           | worldsayshi wrote:
           | Hmm, extractnet seems somewhat promising:
           | 
           | https://github.com/currentslab/extractnet
        
             | Mathnerd314 wrote:
             | That does a list of blocks and "cheats" by using heavily-
             | engineereed features such as Readability's algorithm. It is
             | suitable for some purposes, I guess. But the paper I am
             | talking about, https://arxiv.org/pdf/2201.10608, does self-
             | supervised learning.
        
         | zamfi wrote:
         | This has not been my experience, to be honest -- I wrote a
         | pretty complex scraper for extracting portions of a page and
         | structuring their contents into JSON, using ChatGPT-4, about a
         | year ago and it worked pretty well. (But not "well" in the
         | sense that a non-programmer would've been able to do this, if
         | that's your bar.)
         | 
         | I even got it usefully updated when the format changed!
        
       | mercurialsolo wrote:
       | I call this movement the operator tool.
       | 
       | Tools will no longer need operators as adding multi modality to
       | tools will ensure we can actually have the operator interface on
       | top of the tool.
       | 
       | Tuning the operator is where the playing field shifts to as
       | operators which can translate fuzzy inputs to creative specs or
       | workflows which can in turn be executed by the downstream engine.
        
       | graypegg wrote:
       | I'm glad the conversation about LLMs in UI is getting more
       | nuanced!
       | 
       | There was a while there where it seemed like conversational
       | (either text or by voice-to-text) interfaces were the only way
       | people could imagine using LLMs. Everything being an empty text
       | box staring back at you.
       | 
       | It seems like that may have just been due to ease of
       | implementation to an API. Now that we've all had some time to
       | work a bit, some interesting UI experiments are starting to peek
       | out.
        
       | gklitt wrote:
       | Post author here. Just wanted to link to a talk that I gave which
       | expands on the ideas in this essay and shows a couple evocative
       | demos to make it more concrete:
       | 
       | https://youtu.be/bJ3i4K3hefI?si=BCrqvyZiFFur3W9p
        
       | pilgrim0 wrote:
       | Software is a mean to an end. So programming is a mean to a mean
       | to an end. LLMs are also means to an end. Why would we want to
       | use LLMs as a mean to a mean to a mean to an end, when it can be
       | transparently specialized to get users directly to the end? I
       | think end-user programming has to be a fallacy, because I see no
       | one other than programmers wanting it. It's not to say it's an
       | invalid idea, it's more likely misdirected. I understand the
       | feeling that programmers wish more people could yield the
       | generalized control over their computer devices, as programmers
       | have over their own. But do end users actually need that? Should
       | this be a priority, when time is limited and people can spend it
       | doing more fulfilling things than fiddling with machines? Don't
       | they have numerous other things to optimize for in their actual,
       | physical lives? Why would we wish they carry the burden of such
       | frigid discipline when others can do it for them? As far as I can
       | tell, prompting itself already is end user programming, what's
       | lacking are the bridges between the models and diverse effectful
       | APIs. As absurd as it sounds, at whatever level, programming is
       | merely data parameterization over a set of interfaces. It's also
       | what prompting is, except the underlying interface is overly
       | general. So it seems like a viable future should involve
       | standardization efforts so LLMs can invoke APIs on their own, and
       | we provide it with compatible interfaces it can use to service
       | users. In this scenario, the applications behind the endpoints
       | will not merely be stateless request/response interfaces, as they
       | need also to instruct, model and contextualize remote data
       | capture interfaces within the client - generative interfaces.
       | Software can hardly be more malleable than that: contextually
       | generating whatever UI it's needed to achieve a task that was
       | prompted in natural language. Once there's enough composable
       | black-box services accessible via LLMs, there is no need for end
       | users to program anything, they will directly demand the effects.
       | Sure, there can be service-generating services, but I fail to see
       | how users could parameterize such calls while lacking domain
       | knowledge, and while there'll be a direct path to the exact or
       | approximate effect they need in the first place. As for special
       | cases, they will always require special solutions and specialized
       | knowledge, no matter the domain.
        
       | Jonovono wrote:
       | I don't think people are going far enough. There will be no code
       | in 5-10 years.
       | 
       | > Jensen Huang CEO of NVIDIA said: "Every single pixel will be
       | generated soon. Not rendered: generated"
       | (https://x.com/icreatelife/status/1639363377255309328?lang=en)
       | 
       | If we take this to the extreme, user interfaces are going to be
       | generated on the fly, specific for the user. They will adapt to
       | the user based on the device they are using, time of day, what
       | data is being displayed, what the user prefers, etc.
       | 
       | These large models generating views might be streamed from
       | servers (ala stadia), it might pass off some of the work to edge
       | devices.
       | 
       | The models will be able to store things and communicate with
       | other models as needed. Models might spin up that perform certain
       | things well and have access to specific resources.
        
         | _se wrote:
         | Yeah... no chance. There will be no code in 5 years. What a
         | joke. Even if it were technically possible (it's not), the idea
         | that the humans involved would be able to make it happen in
         | such a short amount of time is laughable.
         | 
         | Seriously, think harder about what you're suggesting here. It's
         | ridiculous.
        
           | Jonovono wrote:
           | Dude chill, it's a thought experiment based on how things are
           | moving right now. Maybe i'm off by a magnitude of years, who
           | cares. Whether it happens in 5, 15, 50 years, it's going to
           | happen.
        
             | _se wrote:
             | You didn't present it as a thought experiment, and it's
             | also not something to treat flippantly. If it happens, it
             | will be because we achieve AGI and nothing less. I know
             | it's in vogue to think that's 5 years away right now, but
             | we're not remotely close and it's also in no way
             | inevitable.
             | 
             | If it does come to that, whether or not there is code will
             | be the least of our worries.
        
               | Jonovono wrote:
               | The article of this post is a thought experiment. Totally
               | fair about the timeline and AGI requirement. Throwing
               | around Elon-like estimates over here.
        
         | JamesonNetworks wrote:
         | Imagine a company trying to offer support to interfaces all
         | tailored to a specific user. I can imagine a future where this
         | is viable, but it will def be a longer time span than 5 years
        
           | Jonovono wrote:
           | Yea, timeline is likely way too optimistic.
        
             | Culonavirus wrote:
             | It's like Elon time on steroids.
        
       | p0w3n3d wrote:
       | There are domains that software being static is a guarantee of
       | law obedience. In other words even continuous deployment is
       | undesired in such cases
        
       | dang wrote:
       | Recent and related:
       | 
       |  _Malleable Software in the Age of LLMs (2023)_ -
       | https://news.ycombinator.com/item?id=40188435 - April 2024 (38
       | comments)
        
       ___________________________________________________________________
       (page generated 2024-05-18 23:01 UTC)