Hacker News
points by rvz 1 day ago | 0 comments
So this is yet another rube goldberg machine.

We have gone down this path already in [0] and this is the same thing but overly complicated. This reason is "because LLMs".

Why?

[0] https://arxiv.org/abs/1410.5401

[–] jwitthuhn 1 day ago
It is a great example to refute the common misconception that LLMs are inherently non-deterministic. I see people repeating this a lot and being able to point at a CPU implemented within one is a very strong counter-example.
[–] aerodexis 16 hours ago
LLM != CPU hardcoded into the same architecture used for an LLM. The non-determinism did not go away - all this is doing is intercepting tool-calls produced by qwen and executing that in different layers.

It's truly not that interesting.

[–] thereader12 14 hours ago
The non-deterministic nature is like the main feature. Also, you could be a cpu with enough patience, you would still be non-deterministic.
[–] rvz 1 day ago
> It is a great example to refute the common misconception that LLMs are inherently non-deterministic.

No it isn't.

Realistically the opposite is true in practice and LLMs are really non-deterministic beyond simplistic experiments such as this in useful activities in production. Even with hacks such as "setting temp=0" (which no-one seriously does) to "achieve determinism", was one of the most common misconceptions ever propagated by "AI engineers".

So using tiny slop experiments aren't really useful as a "strong counter-example". In fact this is a very weak one.