Malleable Software in the Age of LLMs (2023)
geoffreylitt.com
Malleable Software in the Age of LLMs (2023)
1–10 of 39 posts
Re: Malleable Software in the Age of LLMs (2023)
#2> Until now, that vision has been bottlenecked on turning fuzzy informal intent into formal, executable code
Software has been and always will be fundamentally a problem of communication. What many don't realize is that the true challenge of communication is not one of transmission, but clarity of thought and understanding. Any tool, software language, or AI coder will still be limited by the clarity and completeness of the specs presented. What is software after all but complete and precise specs? Nothing will ever turn your fuzzy intent into your clear best interest. If you don't have clarity of thought, no intelligence in the world can help you.
That's not to say I disagree with the author, I agree that more complex creative power will be accessible to a greater number of people, but I think the intrinsic efficiency limit of communication will always be more difficult than people think.
Re: Malleable Software in the Age of LLMs (2023)
#3> Until now, that vision has been bottlenecked on turning fuzzy informal intent into formal, executable code Software has been and always will be fundamentally a problem of communication. What many don't realize is that the true challenge of communication is not one of transmission, but clarity of thought and understanding. Any tool, software language, or AI coder will still be limited by the clarity and completeness…
Agree. Even though I only have twelve years of experience writing software professionally I started to use LLMs more and more in the past few months to write my code for me given a specification of the task. The top commercial LLMS usually do a good job but often fail catastrophically, especially on esoteric projects. I feel like I am slowly developing into a lawyer because of how thoroughly I have to spec out the problem at hand to give enough context to get exactly what I want.
Re: Malleable Software in the Age of LLMs (2023)
#4> Until now, that vision has been bottlenecked on turning fuzzy informal intent into formal, executable code Software has been and always will be fundamentally a problem of communication. What many don't realize is that the true challenge of communication is not one of transmission, but clarity of thought and understanding. Any tool, software language, or AI coder will still be limited by the clarity and completeness…
Agree. Even though I only have twelve years of experience writing software professionally I started to use LLMs more and more in the past few months to write my code for me given a specification of the task. The top commercial LLMS usually do a good job but often fail catastrophically, especially on esoteric projects. I feel like I am slowly developing into a lawyer because of how thoroughly I have to spec out the pr…
> I feel like I am slowly developing into a lawyer
Law is what you get when you're silly enough to attempt to spec a formal system in an informal language.
Re: Malleable Software in the Age of LLMs (2023)
#5> Until now, that vision has been bottlenecked on turning fuzzy informal intent into formal, executable code Software has been and always will be fundamentally a problem of communication. What many don't realize is that the true challenge of communication is not one of transmission, but clarity of thought and understanding. Any tool, software language, or AI coder will still be limited by the clarity and completeness…
The same points you made make me wonder if end users even want to modify or write a program.
Even if it's possible, it's still a lot of work. I just don't see that as the typical consumer behavior.
Re: Malleable Software in the Age of LLMs (2023)
#6> Until now, that vision has been bottlenecked on turning fuzzy informal intent into formal, executable code Software has been and always will be fundamentally a problem of communication. What many don't realize is that the true challenge of communication is not one of transmission, but clarity of thought and understanding. Any tool, software language, or AI coder will still be limited by the clarity and completeness…
The same points you made make me wonder if end users even want to modify or write a program. Even if it's possible, it's still a lot of work. I just don't see that as the typical consumer behavior.
The typical consumer isn't empowered to modify or write a program, so why would they entertain the idea?
Re: Malleable Software in the Age of LLMs (2023)
#7> Until now, that vision has been bottlenecked on turning fuzzy informal intent into formal, executable code Software has been and always will be fundamentally a problem of communication. What many don't realize is that the true challenge of communication is not one of transmission, but clarity of thought and understanding. Any tool, software language, or AI coder will still be limited by the clarity and completeness…
> Software has been and always will be fundamentally a problem of communication.
its a problem of communication with a system. that system can be a human, a group of humans, some esoteric knowledge graph, internet or even a single webpage. i believe the author here is focusing on generative UIs from a software developer standpoint. this is just one form of interaction/communication and could be wrong to be generalized across scenarios.
i have been thinking about highly lossless and efficient forms of communication between a human and a system. keep converging to voice agents where if they feel alot human(something similar to the hume demo) then it can be the default mode of how a human interacts with a system. again, this will be a specific setting and sounds more consumer-ish. a clear contrast to what the author intends to write.
Re: Malleable Software in the Age of LLMs (2023)
#8> Until now, that vision has been bottlenecked on turning fuzzy informal intent into formal, executable code Software has been and always will be fundamentally a problem of communication. What many don't realize is that the true challenge of communication is not one of transmission, but clarity of thought and understanding. Any tool, software language, or AI coder will still be limited by the clarity and completeness…
The same points you made make me wonder if end users even want to modify or write a program. Even if it's possible, it's still a lot of work. I just don't see that as the typical consumer behavior.
Software often doesn't do the thing you want to do.
It almost does it.
Or it can just-just do it with contortions and a lot of repetitive toil on your side.
I think writing little plugins and drivers to do the thing you want with an LLM is something that could be built into a lot of software.
I don't think LLM can architect and build whole systems yet, but this niche is something that can be done.
Re: Malleable Software in the Age of LLMs (2023)
#9> Until now, that vision has been bottlenecked on turning fuzzy informal intent into formal, executable code Software has been and always will be fundamentally a problem of communication. What many don't realize is that the true challenge of communication is not one of transmission, but clarity of thought and understanding. Any tool, software language, or AI coder will still be limited by the clarity and completeness…
The same points you made make me wonder if end users even want to modify or write a program. Even if it's possible, it's still a lot of work. I just don't see that as the typical consumer behavior.
I have yet to meet a non-dev who wants to write or modify software themselves. Quite a few people still don't know that it's the software that makes appliances and devices do things and that it is written. They just don't know what software is so how would they know where to begin writing or modifying code?
Re: Malleable Software in the Age of LLMs (2023)
#10Earlier quoted context omitted.
The same points you made make me wonder if end users even want to modify or write a program. Even if it's possible, it's still a lot of work. I just don't see that as the typical consumer behavior.
Software often doesn't do the thing you want to do. It almost does it. Or it can just-just do it with contortions and a lot of repetitive toil on your side. I think writing little plugins and drivers to do the thing you want with an LLM is something that could be built into a lot of software. I don't think LLM can architect and build whole systems yet, but this niche is something that can be done.
I am not sure that LLMs change much with regards to malleable software. A lot of software used to be somewhat malleable [1]. But that got removed, because it wasn't A/B testable or it wasn't the most easy implementation thinkable. Those two points are not changed by LLMs. Therefore, I doubt we will see a resurgence of malleable or at least configurable and scriptable software. Although, I would love to see it. Even those small features to adapt the application to your style of working instead of the other way around was extremely useful, imho.
[1] There was a time, when it was considered a standard feature of a UI that you could change keyboard shortcuts and toolbars. MacOS and Mac OS X even had an API that end users could use to script across multiple applications. Amiga OS had something similar based on the language Rexx.