Am I wrong to think that the answer is obvious? I mean, who wants web apps to behave differently every time you interact with them?
You or your coworker are not a web app. You can do some of the things that web apps can, and many things that a web app can't, but neither is because of the modality.
Coded determinism is hard for many problems and I find it entirely plausible that it could turn out to be the wrong approach in software, that is designed to solve some level of complex problems more generally. Average humans are pretty great at solving a certain class of complex problems that we tried to tackle unsuccessfully with many millions lines of deterministic code, or simply have not had a handle on at all, like (like build a great software CEO).
Okay but when I start my car I want to drive it, not fuck it.
If we were in an imagined world and you are headed to work
You either walk out your door and there is a self driving car, or you walk out of your door and there is a train waiting for you or you walk out of your door and there is a helicopter or you walk out of your door and there is a literal worm hole.
Let's say all take the same amount of time, are equally safe, same cost, have the same amenities inside, and "feel the same" - would you care if it were different every day?
I don't think I would.
Maybe the wormhole causes slight nausea ;)
In order to get to your destination, you need to explain where you want to go. Whatever you call that “imperative language”, in order to actually get the thing you want, you have to explain it. That’s an unavoidable aspect of interacting with anything that responds to commands, computer or not.
If the AI misunderstands those instructions and takes you to a slightly different place than you want to go, that’s a huge problem. But it’s bound to happen if you’re writing machine instructions in a natural language like English and in an environment where the same instructions aren’t consistently or deterministically interpreted. It’s even more likely if the destination or task is particularly difficult/complex to explain at the desired level of detail.
There’s a certain irreducible level of complexity involved in directing and translating a user’s intent into machine output simply and reliably that people keep trying to “solve”, but the issue keeps reasserting itself generation after generation. COBOL was “plain english” and people assumed it would make interacting with computers like giving instructions to another employee over half a century ago.
The primary difficulty is not the language used to articulate intent, the primary difficulty is articulating intent.
The specific events that follow when asking a taxi driver where to go may not be exactly repeatable, but reality enforces physical determinism that is not explicitly understood by probabilistic token predictors. If you drive into a wall you will obey deterministic laws of momentum. If you drive off a cliff you will obey deterministic laws of gravity. These are certainties, not high probabilities. A physical taxi cannot have a catastrophic instant change in implementation and have its wheels or engine disappear when it stops to pick you up. A human taxi driver cannot instantly swap their physical taxi for a submarine, they cannot swap new york with paris, they cannot pass through buildings… the real world has a physically determined option-space that symbolic token predictors don’t understand yet.
And the reason humans are good at interpreting human intent correctly is not just that we’ve had billions of years of training with direct access to physical reality, but because we all share the same basic structure of inbuilt assumptions and “training history”. When interacting with a machine, so many of those basic unstated shared assumptions are absent, which is why it takes more effort to explicitly articulate what it is exactly that you want.
We’re getting much better at getting machines to infer intent from plain english, but even if we created a machine which could perfectly interpret our intentions, that still doesn’t solve the issue of needing to explain what you want in enough detail to actually get it for most tasks. Moving from point A to point B is a pretty simple task to describe. Many tasks aren’t like that, and the complexity comes as much from explaining what it is you want as it does from the implementation.
it's not as far as your experience goes - you press pedal, it accelerates. You turn the steering, it goes the way it turns. What the car does is deterministic.
More importantly, it does this every time, and the amount of turning (or accelerating) is the same today as it was yesterday.
If an LLM interpreted those inputs, can you say with confidence, that you will accelerate in a way that you predicted? If that is the case, then i would be fine with an LLM interpreted input to drive. Otherwise, how do you know, for sure, that pressing the brakes will stop the car, before you hit somebody in front of you?
of course, you could argue that the input is no longer your moving the brake pads etc - just name a destination and you get there, and that is suppose to be deterministic, as long as you describe your destination correctly. But is that where LLM is at today? or is that the imagined future of LLMs?
It's the same as having a function called "factorial" but you change the multiplication operation to addition instead.
This can be answered though, albeit imperfectly. On a more reductionist level, we are the cosmos experiencing itself. Now there are many ways to approach this. But just providing us with the right chemicals to feel pleasure/satisfaction is a step backwards. All the evolution of a human being, just to end up functionally like an amoeba or a bacteria.
So we need to retrace our steps backwards in this thought process.
I could write a long essay on this.
But, to exist in first place, and to keep existing against all the constraints of the universe, is already pretty fucking amazing.
Whether we do all the things we do, just in order to stay alive and keep existing, or if the point is to be the cosmos “experiencing itself”, is pretty much two sides of the same coin.
When you suddenly realize walking down the street that the very high fentanyl zombie is having a better day than you are.
Yeah, you can push the button in your brain that says "You won the game." However, all those buttons were there so you would self-replicate energy efficient compute. Your brain runs on 10 watts after all. It's going to take a while for AI to get there, especially without the capability for efficient self-repair.
In one scenario every atom's trajectory was destined from the creation of time and we're just sitting in the passenger seat watching. In another, if we do have free will then we control the "real world" underneath - the quantum and particle realms - as if through a UI. In the pod scenario, we are just blobs experiencing chemical reactions through some kind of translation device - but aren't we the same in the other scenarios too?
Every reason people prefer a car or bike over the bus is a reason non-deterministic agents are a bad interface.
And that analogy works as a glimpse into the future - we’re looking at a fast approaching world where LLMs are the interface to everything for most of us - except for the wealthy, who have access to more deterministic services or actual human agents. How long before the rich person car rental service is the only one with staff at the desk, and the cheaper options are all LLM based agents? Poor people ride the bus, rich people get to drive.
It has always seemed to me that workflow or processes need to be deterministic and not decided by an LLM.
Either way, these silly reductionist games aren't addressing the point: if I just want to get from A to B then I definitely want the absolute minimum of unpredictability in how I do it.
I wonder now, if everything is always different and suddenly every day would be the same. How many times as terrifying would that be compared to the opposite?
Your ancestors didn't want horses and carts, bicycles, shoes - they wanted the solutions of the day to the same scenarios above.
To dismiss the entire universe and its hostilities towards our existence and the workarounds we invent in response as mere means to an end rather than our essence is truly wild.
My point was that there is no true end goal as long as whims continue. The need to craft yet more means is equally endless. The crafting is the primary human experience, not the using. The using of a means inevitably becomes transparent and boring.
A job is better if your coworkers are of a caliber that they become a secondary family.
Are you suggesting that an average user would want to precisely describe in detail what they want, every single time, instead of clicking on a link that gives them what they want?
The average user may not care exactly what the mechanic does to fix your car, but they do expect things to be repeatable. If car repair LLMs function anything like coding LLMs, one request could result in an oil change, while a similar request could end up with an engine replacement.
One could imagine a hypothetical AI model that can do a pretty good job of understanding vague requests, properly refusing irrelevant requests (if you ask a mechanic to bake you a cake he'll likely tell you to go away), and behaving more or less consistently. It is acceptable for an AI-based backend to have a non-zero failure rate. If a mechanic was distracted or misheard you or was just feeling really spiteful, it's not inconceivable that he would replace your engine instead of changing your oil. The critical point is that this happens very, very rarely and 99.99% of the time he will change your oil correctly. Current LLMs have far too high of a failure rate to be useful, but having a failure rate at all is not a non-starter for being useful.
Even if it is possible, I’m not sure if we will ever have the compute power to run all or even a significant portion of the world’s computations through LLMs.
LLMs are, of course, bad. Or not good enough, at least. But suppose they are. Suppose they're perfect.
Would I rather use an app or just directly interface with an LLM? The LLM might be quicker and easier. I know, for example, ordering takeout is much faster if I just call and speak to a person.
Yes but the same LLM works very differently on each request. Even ignoring non-determinism, extremely minor differences in wording that a human mechanic wouldn’t even notice will lead to wildly different answers.
> LLMs are, of course, bad. Or not good enough, at least. But suppose they are. Suppose they're perfect.
You’re just talking about magic at that point.
But suppose the do become “perfect”, I’m skeptical we’ll ever have the compute resources to replace a significant fraction of computation with LLMs.
So even if it would be better to have more flexibility, most business won't want it.
I can speculate about what LLM-first software and businesses might look like and I find some of those speculations more attractive than what's currently on offer from existing companies.
The first one, which is already happening to some degree on large platforms like X, is LLM powered social media. Instead of having a human designed algorithm handle suggestions you hand it over to an LLM to decide but it could go further. It could handle customizing the look of the client app for each user, it could provide goal based suggestions or search so you could tell it what type of posts or accounts you're looking for or a reason you're looking for them e.g. "I want to learn ML and find a job in that field" and it gives you a list of users that are in that field, post frequent and high quality educational material, have demonstrated willingness to mentor and are currently not too busy to do so as well as a list of posts that serve as a good starting point, etc.
The difference in functionality would be similar to the change from static websites to dynamic web apps. It adds even more interactivity to the page and broadens the scope of uses you can find for it.
Websites are tools. Tools being non-deterministic can be a really big problem.
knows where we’d end up?
On the other hand the logs might be a great read.
Talk about a nonsensical non-sequitur, but I’ll bite. People want those to be deterministic too, to a large extent.
When people cook a meal with the same ingredients and the same times and processes (like parameters to a function), they expect it to taste about the same, they never expect to cook a pizza and take a salad out of the oven.
When they have sex, people expect to ejaculate and feel good, not have their intercourse morph into a drag race with a clown half-way though.
And when they want a “solution”, they want it to be reliable and trustworthy, not have it shit the bed unpredictably.
When products have limitations, those are usually acceptable to me if I know what they are or if I can find out what the breaking point is.
If the breaking point was me speaking a bit unclearly, I'd speak more clearly. If the breaking point was complex questions, I'd ask simpler ones. If the breaking point is truly random, I simply stop using the service because it's unpredictable and frustrating.
Stellar description.
In the end, useful stuff is built by people caring about the details. This will always be true. I think in LLMs and broadly AI people see an escape valve from that where the thinking about the details can be taken off their hands, and that's appealing, but it won't work in exactly the same way that having a human take the details off your hands doesn't usually work that well unless you yourself understand the details to a large extent (not necessarily down to the atoms, but at the point of abstraction where it matters, which in software is mostly about deterministically how do the logic flows of the thing actually work and why).
I think a lot of people just don't intuit this. An illustrative analogy might be something else creative, like music. Imagine the conversation where you're writing a song and discussing some fine point of detail like the lyrics, should I have this or that line in there, and ask someone's opinion, and their answer is 'well listen, I don't really know about lyrics and all of that, but I know all that really matters in the end is the vibe of the song'. That contributes about the same level of usefulness as talking about how software users are ultimately looking for 'solutions' without talking about the details of said software.
speak for yourself
And don't even try to claim there won't ever be any regression: Current LLM-based A.I. will 'happily' lie to you that they passed all tests -- because based on interactions in the past, it has.
For a typical user today’s software isn’t particularly deterministic. Auto updates mean your software is constantly changing under you.
LLMs being inherently non-deterministic means using this technology as the foundation of your UI will mean your UI is also non-deterministic. The changes that stem from that are NOT from any active participation of the authors/providers.
This opens a can of worms where there will always be a potential for the LLM to spit out extremely undesirable changes without anyone knowing. Maybe your bank app one day doesn't let you access your money. This is a danger inherent and fundamental to LLMs.
Consider this: the bank teller is non-deterministic, too. They could give you 500 dollars of someone else's money. But they don't, generally.
It will be difficult to incorporate relative access or restrictions to features with respect to users current/known state or actions. Might as well write the entire web app at that point.
I think, if we can efficiently capture a way to "make" LLMs conform to a set of processes, you can cut out the app and just let the LLM do it. I don't think this makes any sense for maybe the next decade, but perhaps at some point it will. And, in such time, software engineering will no longer exist.
The LLM example gives you a completely different UI on _every_ page load.
That’s very different from companies moving around buttons occasionally and rarely doing full redesigns
1. Outputting text (or, sometimes, images).
2. No long term storage except, rarely, closed-source "memory" implementations that just paste stuff into context without much user or LLM control.
This is a really neat glimpse of a future where LLMs can have much richer output and storage. I don't think this is interesting because you can recreate existing apps without coding... But I think it's really interesting as a view of a future with much richer, app-like responses from LLMs, and richer interactions — e.g. rather than needing to format everything as a question, the LLM could generate links that you click on to drill into more information on a subject, which end up querying the LLM itself! And similarly it can ad-hoc manage databases for memory+storage, etc etc.
LLM is just one model used in A.I. It's not a panacea.
For generating deterministic output, probably a combination of Neural Networks and Genetic Programming will be better. And probably also much more efficient, energy-wise.
Not quite the case. Temperature 0 is not the same as random seed. Also there are downsides to lowering temperature (always choosing the most probable next token).
We absolutely should want developers to think.
This project would be the developer tool used to produce interactive tools for end users.
More practically, it just redefines the developer's position; the developer and end-user are both "users". So the developer doesn't need to think AND the user doesn't need to think.
Technically everyone, we stopped using static pages a while ago.
Imagine pages that can now show you e.g. infinitely customizable UI; or, more likely, extremely personalized ads.
When I go to the dmv website to renew my license, I want it to renew my license every single time
Yeah, NO.
Product owners were happy.
Until users came for us with pitchforks as they didn’t want stuff to change constantly.
We backed out to releasing on monthly cadence.