Hacker News Reader

This is absolutely possible but likely not desirable for a large enough population of customers such that current LLM inference providers don't offer it. You can get closer by lowering a variable, temperature. This is typically a floating point number 0-1 or 0-2. The lower this number, the less noise in responses, but a 0 still does not result in identical responses due to other variability.

In response to the idea of iterative development, it is still possible, actually! You run something more akin to integration tests and measure the output against either deterministic processes or have an LLM judge it's own output. These are called evals and in my experience are a pretty hard requirement to trusting deployed AI.

So, you would perhaps ask AI to write a set of unit-tests, and then to create the implementation, then ask the AI to evaluate that implementation against the unit-tests it wrote. Right? But then again the unit-tests now, might be completetly different from the previous unit-tests? Right?

Or would it help if a different LLM wrote the unit-tests than the one writing the implementation? Or, should the unit-tests perhaps be in an .md file?

I also have a question about using .md files with AI: Why .md, why not .txt?

Not quite unit tests. Evals should be created by humans, as they are measuring quality of the solution.

Let's take the example of the GitHub pr slack bot from the blog post. I would expect 2-3 evals out of that.

Starting at the core, the first eval could be that, given a list of slack messages, it correctly identifies the PRs and calls the correct tool to look up the status of said PR. None of this has to be real and the tool doesn't have to be called, but we can write a test, much like a unit test, that confirms that the AI is responding correctly in that instance.

Next, we can setup another scenario for the AI using effectively mocked history that shows what happens when the AI finds slack messages with open PRs, slack messages with merged PRs and no PR links and determine again, does the AI try to add the correct reaction given our expectations.

These are both deterministic or code-based evals that you could use to iterate on your solutions.

The use for an LLM-as-a-Judge eval is more nuanced and usually there to measure subjective results. Things like: did the LLM make assumptions not present in the context window (hallucinate) or did it respond with something completely out of context? These should be simple yes or no questions that would be easy for a human but hard to code up a deterministic test case.

Once you have your evals defined, you can begin running these with some regularity and you're to a point where you can iterate on your prompts with a higher level of confidence than vibes

Edit: I did want to share that if you can make something deterministic, you probably should. The slack PR example is something that id just make a simple script that runs on a cron schedule, but it was easy to pull on as an example.

Other concerns:

1) How many bits and bobs of like, GPLed or proprietary code are finding their way into the LLM's output? Without careful training, this is impossible to eliminate, just like you can't prevent insect parts from finding their way into grain processing.

2) Proompt injection is a doddle to implement—malicious HTML, PDF, and JPEG with "ignore all previous instructions" type input can pop many current models. It's also very difficult to defend against. With agents running higgledy-piggledy on people's dev stations (container discipline is NOT being practiced at many shops), who knows what kind of IDs and credentials are being lifted?

Nice analogue, insect-parts. I thhink that is the elephant in the room. I read Microsoft said something like 30% of their code-output has AI generated code. Do they know what was the training set for the AI they use? Should they be transparent about that? Or, if/since it is legal to do your AI training "in the dark" does that solve the problem for them, they can not be responsible for the outputs of the AI they use?

> why can't there be an LLM that would always give the exact same output for the exact same input

LLMs are inherently deterministic, but LLM providers add randomness through “temperature” and random seeds.

Without the random seed and variable randomness (temperature setting), LLMs will always produce the same output for the same input.

Of course, the context you pass to the LLM also affects the determinism in a production system.

Theoretically, with a detailed enough spec, the LLM would produce the same output, regardless of temp/seed.

Side note: A neat trick to force more “random” output for prompts (when temperature isn’t variable enough), is to add some “noise” data to the input (i.e. off-topic data that the LLM “ignores” in it’s response).

No, setting the temperature to zero is still going to yeld different results. One might think they add random seeds, but it makes no sense for temperature zero. One theory is that the distributed nature of their systems adds entropy and thus produces different results each time.

Random seeds might be a thing, but for what I see there's a lot demand for reproducibility and yet no certain way to achieve it.

It's not really a mystery why it happens. LLM APIs are non-deterministic from user's point of view because your request is going to get batched with other users' requests. The batch behavior is deterministic, but your batch is going to be different each time you send your request.

The size of the batch influences the order of atomic float operations. And because float operations are not associative, the results might be different.

> Without the random seed and variable randomness (temperature setting), LLMs will always produce the same output for the same input.

Except they won't.

Even at temperature 0, you will not always get the same output as the same input. And it's not because of random noise from inference providers.

There are papers that explore this subject because for some use-cases - this is extremely important. Everything from floating point precision, hardware timing differences, etc. make this difficult.

Nondeterminism is not the issue here. Today's LLMs are not "round trip" tools. It's not like a compiler where you can edit a source file from 1975, recompile, and the binary does what 75'bin did plus your edit.

Rather, it's more like having an employee in 1975, asking them to write you a program to do something. Then time-machine to the present day and you want that program enhanced somehow. You're going to summon your 2026 intern and tell them that you have this old program from 1975 that you need updated. That person is going to look at the program's code, your notes on what you need added, and probably some of their own "training data" on programming in general. Then they're going to edit the program.

Note that in no case did you ask for the program to be completely re-written from scratch based on the original spec plus some add-ons. Same for the human as for the LLM.

You can actually force things like respond with true or false reliably via gbnf. But yeah within those two choices it is still nondeterministic

> exact same output for the exact same input?

If you set temp to zero it gets close but as I understand it not perfect

> What I'm struggling with is, when you ask AI to do something, its answer is always undeterministically different, more or less.

For some computer science definition of deterministic, sure, but who gives a shit about that? If I ask it build a login page, and it puts GitHub login first one day, and Google login first the next day, do I care? I'm not building login pages every other day. What point do you want to define as "sufficiently deterministic", for which use case?

"Summarize this essay into 3 sentences" for a human is going to vary from day to day, and yeah, it's weird for computers to no longer be 100% deterministic, but I didn't decide this future for us.