Why do people keep having this reaction to something we're already used to? When you're developing against an API, you're already doing the same thing, planning for what happens when the request hangs, or fails completely, or gives a different response, and so on. Same for basically any IO.
It's almost not even new, just that it generates text instead of JSON, or whatever. But we've already been doing "indeterministic programming" for a long time, where you cannot always assume a function 100% returns what it should all the time.
You’re right about the trees but wrong (hear me out) about the forest.
Yes, programming isn’t always deterministic, not just due to the leftpad API endpoint being down, but by design - you can’t deterministically tell which button the user is going to click. So far so good.
But, you program for the things that you expect to happen, and handle the rest as errors. If you look at the branching topology of well-written code, the majority of paths lead to an error. Most strings are not valid json, but are handled perfectly well as errors. The paths you didn’t predict can cause bugs, and those bugs can be fixed.
Within this system, you have effective local determinism. In practice, this gives you the following guarantee: if the program executed correctly until point X, the local state is known. This state is used to build on top of that, and continue the chain of bounded determinism, which is so incredibly reliable on modern CPUs that you can run massive financial transactions and be sure it works. Or, run a weapons system or a flight control system.
So when people point out that LLMs are non-deterministic (or technically unstable, to avoid bike-shedding), they mean that it’s a fundamentally different type of component in an engineering system. It’s not like retrying an HTTP request, because when things go wrong it doesn’t produce “errors”, it produces garbage that looks like gold.
Programmers aren't deterministic either. If I ask ten programmers to come up with a solution to the same problem, I'm not likely to get ten identical copies. Different programmers, even competent experienced programmers, might have different priorities that aren't in the requirements. For example, trading off program maintainability or portability over performance.
The same could apply to LLMs, or even different runs from the same LLMs.
No but programs are. An LLM can be a programmer too, but it’s not a program the way we want and expect programs to behave: deterministically. Even if a programmer could perform a TLS handshake manually very fast, ignoring the immense waste of energy, the program is a much better engineering component, simply because it is deterministic and does the same thing every time. If there’s a bug, it can be fixed, and then the bug will not re-appear.
> If I ask ten programmers to come up with a solution to the same problem, I'm not likely to get ten identical copies.
Right, but you only want one copy. If you need different clients speaking with each other you need to define a protocol and run conformance tests, which is a lot of work. It’s certainly doable, but you don’t want a different program every time you run it.
I really didn’t expect arguing for reproducibility in engineering to be controversial. The primary way we fix bugs is by literally asking for steps to reproduction. This is not possible when you have a chaos agent in the middle, no matter how good. The only reasonable conclusion is to treat AI systems as entirely different components and isolate them such that you can keep the boring predictability of mechanistic programs. Basically separating engineering from the alchemy.
Not really, we have many implementations of web servers or ftp clients, but they all follow the same protocol. So you can pair any two things that talk the same protocol and have a consistent systems. If you gave ten programmers a specs, you get ten implementations that follows the specs. With LLMs, you get random things.
Why would we embrace that even more? In Software Development we try to keep things deterministic as much as possible. The more variables we're introducing into our software, the more complicated it becomes.
The whole notion of adding LLM prompts as a replacement for code just seems utterly insane to me. It would be a massive waste of resources as we're reprompting AI a lot more frequently than we need to. Also must be fun to debug, as it may or may not work correctly depending on how the LLM model is feeling at that moment. Compilation should always be deterministic, given the same environment.
It's almost not even new, just that it generates text instead of JSON, or whatever. But we've already been doing "indeterministic programming" for a long time, where you cannot always assume a function 100% returns what it should all the time.